< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 73 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 0.3185. Min Range: -0.3185

Max Act: 0.3081. Min Act: -0.0001

Data Index: 488949 (The Pile)

Max Activating Token Index: 281

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.3185. Min Range: -0.3185

Max Act: 0.2969. Min Act: -0.0001

Data Index: 1607196 (The Pile)

Max Activating Token Index: 653

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.3185. Min Range: -0.3185

Max Act: 0.3022. Min Act: -0.0001

Data Index: 1182737 (The Pile)

Max Activating Token Index: 841

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.3185. Min Range: -0.3185

Max Act: 0.3185. Min Act: -0.0001

Data Index: 351255 (The Pile)

Max Activating Token Index: 584

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.3185. Min Range: -0.3185

Max Act: 0.2732. Min Act: -0.0001

Data Index: 1407671 (The Pile)

Max Activating Token Index: 297

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.3185. Min Range: -0.3185

Max Act: 0.2875. Min Act: -0.0001

Data Index: 1273234 (The Pile)

Max Activating Token Index: 928

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.3185. Min Range: -0.3185

Max Act: 0.2835. Min Act: -0.0001

Data Index: 113750 (The Pile)

Max Activating Token Index: 277

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.3185. Min Range: -0.3185

Max Act: 0.2530. Min Act: -0.0001

Data Index: 5164 (The Pile)

Max Activating Token Index: 310

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.3185. Min Range: -0.3185

Max Act: 0.2658. Min Act: -0.0000

Data Index: 1082624 (The Pile)

Max Activating Token Index: 426

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.3185. Min Range: -0.3185

Max Act: 0.2729. Min Act: -0.0001

Data Index: 1907518 (The Pile)

Max Activating Token Index: 976

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.3185. Min Range: -0.3185

Max Act: 0.2545. Min Act: -0.0001

Data Index: 684261 (The Pile)

Max Activating Token Index: 333

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.3185. Min Range: -0.3185

Max Act: 0.2542. Min Act: -0.0001

Data Index: 1969964 (The Pile)

Max Activating Token Index: 852

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.3185. Min Range: -0.3185

Max Act: 0.2566. Min Act: -0.0001

Data Index: 1758514 (The Pile)

Max Activating Token Index: 995

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.3185. Min Range: -0.3185

Max Act: 0.2358. Min Act: -0.0001

Data Index: 1311816 (The Pile)

Max Activating Token Index: 934

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.3185. Min Range: -0.3185

Max Act: 0.2672. Min Act: -0.0001

Data Index: 686764 (The Pile)

Max Activating Token Index: 288

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.3185. Min Range: -0.3185

Max Act: 0.2841. Min Act: -0.0001

Data Index: 519585 (The Pile)

Max Activating Token Index: 601

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.3185. Min Range: -0.3185

Max Act: 0.2405. Min Act: -0.0001

Data Index: 1434137 (The Pile)

Max Activating Token Index: 778

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.3185. Min Range: -0.3185

Max Act: 0.2620. Min Act: -0.0001

Data Index: 1394345 (The Pile)

Max Activating Token Index: 898

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.3185. Min Range: -0.3185

Max Act: 0.2527. Min Act: -0.0001

Data Index: 1918547 (The Pile)

Max Activating Token Index: 773

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.3185. Min Range: -0.3185

Max Act: 0.2334. Min Act: -0.0001

Data Index: 1200968 (The Pile)

Max Activating Token Index: 606

Click toggle to see full text

Truncated

Full Text #19