Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 1932 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.4969. Min Range: -0.4969

Max Act: 0.4906. Min Act: -0.0000

Data Index: 790386 (The Pile)

Max Activating Token Index: 553

Text #1

Max Range: 0.4969. Min Range: -0.4969

Max Act: 0.4969. Min Act: -0.0000

Data Index: 1776934 (The Pile)

Max Activating Token Index: 206

Text #2

Max Range: 0.4969. Min Range: -0.4969

Max Act: 0.4841. Min Act: -0.0000

Data Index: 1985666 (The Pile)

Max Activating Token Index: 267

Text #3

Max Range: 0.4969. Min Range: -0.4969

Max Act: 0.4518. Min Act: -0.0000

Data Index: 1701768 (The Pile)

Max Activating Token Index: 529

Text #4

Max Range: 0.4969. Min Range: -0.4969

Max Act: 0.4632. Min Act: -0.0000

Data Index: 1864799 (The Pile)

Max Activating Token Index: 901

Text #5

Max Range: 0.4969. Min Range: -0.4969

Max Act: 0.4521. Min Act: -0.0000

Data Index: 1537121 (The Pile)

Max Activating Token Index: 819

Text #6

Max Range: 0.4969. Min Range: -0.4969

Max Act: 0.4573. Min Act: -0.0000

Data Index: 1608953 (The Pile)

Max Activating Token Index: 993

Text #7

Max Range: 0.4969. Min Range: -0.4969

Max Act: 0.4248. Min Act: -0.0000

Data Index: 1172343 (The Pile)

Max Activating Token Index: 505

Text #8

Max Range: 0.4969. Min Range: -0.4969

Max Act: 0.4383. Min Act: -0.0000

Data Index: 1426080 (The Pile)

Max Activating Token Index: 299

Text #9

Max Range: 0.4969. Min Range: -0.4969

Max Act: 0.3764. Min Act: -0.0000

Data Index: 429498 (The Pile)

Max Activating Token Index: 615

Text #10

Max Range: 0.4969. Min Range: -0.4969

Max Act: 0.3831. Min Act: -0.0000

Data Index: 372200 (The Pile)

Max Activating Token Index: 762

Text #11

Max Range: 0.4969. Min Range: -0.4969

Max Act: 0.4113. Min Act: -0.0000

Data Index: 1846758 (The Pile)

Max Activating Token Index: 169

Text #12

Max Range: 0.4969. Min Range: -0.4969

Max Act: 0.3447. Min Act: -0.0000

Data Index: 142658 (The Pile)

Max Activating Token Index: 698

Text #13

Max Range: 0.4969. Min Range: -0.4969

Max Act: 0.3986. Min Act: -0.0000

Data Index: 559371 (The Pile)

Max Activating Token Index: 227

Text #14

Max Range: 0.4969. Min Range: -0.4969

Max Act: 0.4131. Min Act: -0.0000

Data Index: 1190240 (The Pile)

Max Activating Token Index: 507

Text #15

Max Range: 0.4969. Min Range: -0.4969

Max Act: 0.3755. Min Act: -0.0000

Data Index: 1216895 (The Pile)

Max Activating Token Index: 263

Text #16

Max Range: 0.4969. Min Range: -0.4969

Max Act: 0.3450. Min Act: -0.0000

Data Index: 207180 (The Pile)

Max Activating Token Index: 754

Text #17

Max Range: 0.4969. Min Range: -0.4969

Max Act: 0.3635. Min Act: -0.0000

Data Index: 698845 (The Pile)

Max Activating Token Index: 239

Text #18

Max Range: 0.4969. Min Range: -0.4969

Max Act: 0.3333. Min Act: -0.0000

Data Index: 1325221 (The Pile)

Max Activating Token Index: 809

Text #19

Max Range: 0.4969. Min Range: -0.4969

Max Act: 0.3193. Min Act: -0.0000

Data Index: 866199 (The Pile)

Max Activating Token Index: 571