< Prev | Home | Model | Random | Next >

Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 227 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')



Text #0

Max Range: 2.3385. Min Range: -2.3385

Max Act: 2.3385. Min Act: -0.0000

Data Index: 1261968 (The Pile)

Max Activating Token Index: 119

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.3385. Min Range: -2.3385

Max Act: 2.2817. Min Act: -0.0000

Data Index: 1462320 (The Pile)

Max Activating Token Index: 162

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.3385. Min Range: -2.3385

Max Act: 2.2990. Min Act: -0.0000

Data Index: 1279003 (The Pile)

Max Activating Token Index: 149

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.3385. Min Range: -2.3385

Max Act: 2.0338. Min Act: -0.0000

Data Index: 1509063 (The Pile)

Max Activating Token Index: 409

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.3385. Min Range: -2.3385

Max Act: 2.1352. Min Act: -0.0000

Data Index: 1519772 (The Pile)

Max Activating Token Index: 679

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.3385. Min Range: -2.3385

Max Act: 2.1947. Min Act: -0.0000

Data Index: 207145 (The Pile)

Max Activating Token Index: 980

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.3385. Min Range: -2.3385

Max Act: 2.0633. Min Act: -0.0000

Data Index: 596118 (The Pile)

Max Activating Token Index: 108

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.3385. Min Range: -2.3385

Max Act: 2.0493. Min Act: -0.0000

Data Index: 1973653 (The Pile)

Max Activating Token Index: 408

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.3385. Min Range: -2.3385

Max Act: 2.0185. Min Act: -0.0000

Data Index: 1061630 (The Pile)

Max Activating Token Index: 197

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.3385. Min Range: -2.3385

Max Act: 2.0033. Min Act: -0.0000

Data Index: 1840774 (The Pile)

Max Activating Token Index: 391

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.3385. Min Range: -2.3385

Max Act: 1.9933. Min Act: -0.0000

Data Index: 246548 (The Pile)

Max Activating Token Index: 137

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.3385. Min Range: -2.3385

Max Act: 2.1040. Min Act: -0.0000

Data Index: 1018442 (The Pile)

Max Activating Token Index: 306

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.3385. Min Range: -2.3385

Max Act: 2.2208. Min Act: -0.0000

Data Index: 1757826 (The Pile)

Max Activating Token Index: 679

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.3385. Min Range: -2.3385

Max Act: 2.1169. Min Act: -0.0000

Data Index: 1498530 (The Pile)

Max Activating Token Index: 675

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.3385. Min Range: -2.3385

Max Act: 2.0886. Min Act: -0.0000

Data Index: 191199 (The Pile)

Max Activating Token Index: 200

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.3385. Min Range: -2.3385

Max Act: 2.1061. Min Act: -0.0000

Data Index: 1453753 (The Pile)

Max Activating Token Index: 300

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.3385. Min Range: -2.3385

Max Act: 2.1990. Min Act: -0.0000

Data Index: 535260 (The Pile)

Max Activating Token Index: 356

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.3385. Min Range: -2.3385

Max Act: 1.9634. Min Act: -0.0000

Data Index: 642266 (The Pile)

Max Activating Token Index: 774

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.3385. Min Range: -2.3385

Max Act: 2.0926. Min Act: -0.0000

Data Index: 1291981 (The Pile)

Max Activating Token Index: 136

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.3385. Min Range: -2.3385

Max Act: 2.0657. Min Act: -0.0000

Data Index: 872082 (The Pile)

Max Activating Token Index: 136

Click toggle to see full text

Truncated

Full Text #19