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

Dataset: The Pile

Neuron 3911 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: 0.8132. Min Range: -0.8132

Max Act: 0.8132. Min Act: -0.0000

Data Index: 469243 (The Pile)

Max Activating Token Index: 448

Text #1

Max Range: 0.8132. Min Range: -0.8132

Max Act: 0.7915. Min Act: -0.0000

Data Index: 234354 (The Pile)

Max Activating Token Index: 91

Text #2

Max Range: 0.8132. Min Range: -0.8132

Max Act: 0.8061. Min Act: -0.0000

Data Index: 1030925 (The Pile)

Max Activating Token Index: 999

Text #3

Max Range: 0.8132. Min Range: -0.8132

Max Act: 0.7890. Min Act: -0.0000

Data Index: 59736 (The Pile)

Max Activating Token Index: 14

Text #4

Max Range: 0.8132. Min Range: -0.8132

Max Act: 0.7040. Min Act: -0.0000

Data Index: 1074282 (The Pile)

Max Activating Token Index: 349

Text #5

Max Range: 0.8132. Min Range: -0.8132

Max Act: 0.6483. Min Act: -0.0000

Data Index: 575015 (The Pile)

Max Activating Token Index: 143

Text #6

Max Range: 0.8132. Min Range: -0.8132

Max Act: 0.6955. Min Act: -0.0000

Data Index: 455473 (The Pile)

Max Activating Token Index: 828

Text #7

Max Range: 0.8132. Min Range: -0.8132

Max Act: 0.7205. Min Act: -0.0000

Data Index: 408322 (The Pile)

Max Activating Token Index: 282

Text #8

Max Range: 0.8132. Min Range: -0.8132

Max Act: 0.7212. Min Act: -0.0000

Data Index: 79114 (The Pile)

Max Activating Token Index: 592

Text #9

Max Range: 0.8132. Min Range: -0.8132

Max Act: 0.6031. Min Act: -0.0000

Data Index: 1332717 (The Pile)

Max Activating Token Index: 576

Text #10

Max Range: 0.8132. Min Range: -0.8132

Max Act: 0.6716. Min Act: -0.0000

Data Index: 722080 (The Pile)

Max Activating Token Index: 391

Text #11

Max Range: 0.8132. Min Range: -0.8132

Max Act: 0.6675. Min Act: -0.0000

Data Index: 1341775 (The Pile)

Max Activating Token Index: 481

Text #12

Max Range: 0.8132. Min Range: -0.8132

Max Act: 0.7263. Min Act: -0.0000

Data Index: 1118376 (The Pile)

Max Activating Token Index: 563

Text #13

Max Range: 0.8132. Min Range: -0.8132

Max Act: 0.6402. Min Act: -0.0000

Data Index: 1996589 (The Pile)

Max Activating Token Index: 271

Text #14

Max Range: 0.8132. Min Range: -0.8132

Max Act: 0.6304. Min Act: -0.0000

Data Index: 1318552 (The Pile)

Max Activating Token Index: 206

Text #15

Max Range: 0.8132. Min Range: -0.8132

Max Act: 0.6469. Min Act: -0.0000

Data Index: 1418540 (The Pile)

Max Activating Token Index: 478

Text #16

Max Range: 0.8132. Min Range: -0.8132

Max Act: 0.6486. Min Act: -0.0000

Data Index: 1418244 (The Pile)

Max Activating Token Index: 116

Text #17

Max Range: 0.8132. Min Range: -0.8132

Max Act: 0.6244. Min Act: -0.0000

Data Index: 1410432 (The Pile)

Max Activating Token Index: 664

Text #18

Max Range: 0.8132. Min Range: -0.8132

Max Act: 0.5758. Min Act: -0.0000

Data Index: 676914 (The Pile)

Max Activating Token Index: 883

Text #19

Max Range: 0.8132. Min Range: -0.8132

Max Act: 0.6263. Min Act: -0.0000

Data Index: 1045944 (The Pile)

Max Activating Token Index: 443