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

Dataset: The Pile

Neuron 2913 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7520. Min Range: -3.7520

Max Act: 3.7520. Min Act: -0.0000

Data Index: 304751 (The Pile)

Max Activating Token Index: 195

Text #1

Max Range: 3.7520. Min Range: -3.7520

Max Act: 3.4753. Min Act: -0.0000

Data Index: 367168 (The Pile)

Max Activating Token Index: 551

Text #2

Max Range: 3.7520. Min Range: -3.7520

Max Act: 3.3126. Min Act: -0.0000

Data Index: 1176206 (The Pile)

Max Activating Token Index: 70

Text #3

Max Range: 3.7520. Min Range: -3.7520

Max Act: 3.0858. Min Act: -0.0000

Data Index: 312208 (The Pile)

Max Activating Token Index: 95

Text #4

Max Range: 3.7520. Min Range: -3.7520

Max Act: 2.9986. Min Act: -0.0000

Data Index: 752533 (The Pile)

Max Activating Token Index: 145

Text #5

Max Range: 3.7520. Min Range: -3.7520

Max Act: 3.1513. Min Act: -0.0000

Data Index: 1677011 (The Pile)

Max Activating Token Index: 205

Text #6

Max Range: 3.7520. Min Range: -3.7520

Max Act: 3.0937. Min Act: -0.0000

Data Index: 643199 (The Pile)

Max Activating Token Index: 19

Text #7

Max Range: 3.7520. Min Range: -3.7520

Max Act: 3.1277. Min Act: -0.0000

Data Index: 1993044 (The Pile)

Max Activating Token Index: 95

Text #8

Max Range: 3.7520. Min Range: -3.7520

Max Act: 3.0211. Min Act: -0.0000

Data Index: 537995 (The Pile)

Max Activating Token Index: 245

Text #9

Max Range: 3.7520. Min Range: -3.7520

Max Act: 3.4347. Min Act: -0.0000

Data Index: 1716870 (The Pile)

Max Activating Token Index: 782

Text #10

Max Range: 3.7520. Min Range: -3.7520

Max Act: 2.6315. Min Act: -0.0000

Data Index: 129607 (The Pile)

Max Activating Token Index: 36

Text #11

Max Range: 3.7520. Min Range: -3.7520

Max Act: 2.8558. Min Act: -0.0000

Data Index: 1350245 (The Pile)

Max Activating Token Index: 281

Text #12

Max Range: 3.7520. Min Range: -3.7520

Max Act: 2.7120. Min Act: -0.0000

Data Index: 120866 (The Pile)

Max Activating Token Index: 452

Text #13

Max Range: 3.7520. Min Range: -3.7520

Max Act: 2.7724. Min Act: -0.0000

Data Index: 41016 (The Pile)

Max Activating Token Index: 30

Text #14

Max Range: 3.7520. Min Range: -3.7520

Max Act: 2.8685. Min Act: -0.0000

Data Index: 1699899 (The Pile)

Max Activating Token Index: 815

Text #15

Max Range: 3.7520. Min Range: -3.7520

Max Act: 2.7355. Min Act: -0.0000

Data Index: 635105 (The Pile)

Max Activating Token Index: 959

Text #16

Max Range: 3.7520. Min Range: -3.7520

Max Act: 2.7156. Min Act: -0.0000

Data Index: 1740889 (The Pile)

Max Activating Token Index: 345

Text #17

Max Range: 3.7520. Min Range: -3.7520

Max Act: 2.7159. Min Act: -0.0000

Data Index: 1119004 (The Pile)

Max Activating Token Index: 43

Text #18

Max Range: 3.7520. Min Range: -3.7520

Max Act: 2.5760. Min Act: -0.0000

Data Index: 1138628 (The Pile)

Max Activating Token Index: 59

Text #19

Max Range: 3.7520. Min Range: -3.7520

Max Act: 2.6823. Min Act: -0.0000

Data Index: 1249350 (The Pile)

Max Activating Token Index: 74