< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 23 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 1.9219. Min Range: -1.9219

Max Act: 1.9219. Min Act: -0.0001

Data Index: 1907308 (The Pile)

Max Activating Token Index: 366

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 1.9219. Min Range: -1.9219

Max Act: 1.4730. Min Act: -0.0001

Data Index: 1725782 (The Pile)

Max Activating Token Index: 261

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 1.9219. Min Range: -1.9219

Max Act: 1.3303. Min Act: -0.0001

Data Index: 89850 (The Pile)

Max Activating Token Index: 400

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 1.9219. Min Range: -1.9219

Max Act: 1.2966. Min Act: -0.0001

Data Index: 19721 (The Pile)

Max Activating Token Index: 748

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 1.9219. Min Range: -1.9219

Max Act: 1.1854. Min Act: -0.0001

Data Index: 1119879 (The Pile)

Max Activating Token Index: 743

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 1.9219. Min Range: -1.9219

Max Act: 1.2520. Min Act: -0.0001

Data Index: 378097 (The Pile)

Max Activating Token Index: 440

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 1.9219. Min Range: -1.9219

Max Act: 1.1700. Min Act: -0.0001

Data Index: 965394 (The Pile)

Max Activating Token Index: 557

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 1.9219. Min Range: -1.9219

Max Act: 1.1960. Min Act: -0.0001

Data Index: 989390 (The Pile)

Max Activating Token Index: 345

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 1.9219. Min Range: -1.9219

Max Act: 1.1364. Min Act: -0.0001

Data Index: 241401 (The Pile)

Max Activating Token Index: 191

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 1.9219. Min Range: -1.9219

Max Act: 1.1061. Min Act: -0.0001

Data Index: 1441889 (The Pile)

Max Activating Token Index: 148

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 1.9219. Min Range: -1.9219

Max Act: 1.1009. Min Act: -0.0001

Data Index: 303360 (The Pile)

Max Activating Token Index: 428

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 1.9219. Min Range: -1.9219

Max Act: 1.1201. Min Act: -0.0001

Data Index: 832380 (The Pile)

Max Activating Token Index: 549

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 1.9219. Min Range: -1.9219

Max Act: 1.1732. Min Act: -0.0001

Data Index: 83231 (The Pile)

Max Activating Token Index: 252

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 1.9219. Min Range: -1.9219

Max Act: 1.1329. Min Act: -0.0001

Data Index: 353540 (The Pile)

Max Activating Token Index: 501

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 1.9219. Min Range: -1.9219

Max Act: 1.1385. Min Act: -0.0001

Data Index: 458741 (The Pile)

Max Activating Token Index: 173

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 1.9219. Min Range: -1.9219

Max Act: 1.0979. Min Act: -0.0001

Data Index: 158503 (The Pile)

Max Activating Token Index: 440

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 1.9219. Min Range: -1.9219

Max Act: 1.0943. Min Act: -0.0001

Data Index: 1498167 (The Pile)

Max Activating Token Index: 131

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 1.9219. Min Range: -1.9219

Max Act: 0.9998. Min Act: -0.0001

Data Index: 1051514 (The Pile)

Max Activating Token Index: 441

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 1.9219. Min Range: -1.9219

Max Act: 1.1374. Min Act: -0.0001

Data Index: 1605547 (The Pile)

Max Activating Token Index: 638

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 1.9219. Min Range: -1.9219

Max Act: 1.0784. Min Act: -0.0001

Data Index: 1110457 (The Pile)

Max Activating Token Index: 224

Click toggle to see full text

Truncated

Full Text #19