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

Dataset: The Pile

Neuron 3276 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: 1.4884. Min Range: -1.4884

Max Act: 1.4884. Min Act: -0.0000

Data Index: 1047933 (The Pile)

Max Activating Token Index: 625

Text #1

Max Range: 1.4884. Min Range: -1.4884

Max Act: 1.0319. Min Act: -0.0000

Data Index: 874091 (The Pile)

Max Activating Token Index: 49

Text #2

Max Range: 1.4884. Min Range: -1.4884

Max Act: 0.9942. Min Act: -0.0000

Data Index: 1628854 (The Pile)

Max Activating Token Index: 231

Text #3

Max Range: 1.4884. Min Range: -1.4884

Max Act: 0.8143. Min Act: -0.0000

Data Index: 51881 (The Pile)

Max Activating Token Index: 136

Text #4

Max Range: 1.4884. Min Range: -1.4884

Max Act: 0.8592. Min Act: -0.0000

Data Index: 686363 (The Pile)

Max Activating Token Index: 146

Text #5

Max Range: 1.4884. Min Range: -1.4884

Max Act: 0.9138. Min Act: 0.0000

Data Index: 1563834 (The Pile)

Max Activating Token Index: 782

Text #6

Max Range: 1.4884. Min Range: -1.4884

Max Act: 0.7969. Min Act: -0.0000

Data Index: 653621 (The Pile)

Max Activating Token Index: 137

Text #7

Max Range: 1.4884. Min Range: -1.4884

Max Act: 0.8100. Min Act: -0.0000

Data Index: 1401529 (The Pile)

Max Activating Token Index: 675

Text #8

Max Range: 1.4884. Min Range: -1.4884

Max Act: 0.8518. Min Act: -0.0000

Data Index: 1377976 (The Pile)

Max Activating Token Index: 182

Text #9

Max Range: 1.4884. Min Range: -1.4884

Max Act: 0.7960. Min Act: -0.0000

Data Index: 170864 (The Pile)

Max Activating Token Index: 205

Text #10

Max Range: 1.4884. Min Range: -1.4884

Max Act: 0.8379. Min Act: -0.0000

Data Index: 757436 (The Pile)

Max Activating Token Index: 121

Text #11

Max Range: 1.4884. Min Range: -1.4884

Max Act: 0.8088. Min Act: -0.0000

Data Index: 1442385 (The Pile)

Max Activating Token Index: 808

Text #12

Max Range: 1.4884. Min Range: -1.4884

Max Act: 0.7291. Min Act: -0.0000

Data Index: 1663107 (The Pile)

Max Activating Token Index: 789

Text #13

Max Range: 1.4884. Min Range: -1.4884

Max Act: 0.8023. Min Act: -0.0000

Data Index: 725372 (The Pile)

Max Activating Token Index: 624

Text #14

Max Range: 1.4884. Min Range: -1.4884

Max Act: 0.7262. Min Act: -0.0000

Data Index: 1094459 (The Pile)

Max Activating Token Index: 420

Text #15

Max Range: 1.4884. Min Range: -1.4884

Max Act: 0.6927. Min Act: -0.0000

Data Index: 1653462 (The Pile)

Max Activating Token Index: 873

Text #16

Max Range: 1.4884. Min Range: -1.4884

Max Act: 0.7251. Min Act: -0.0000

Data Index: 1126993 (The Pile)

Max Activating Token Index: 406

Text #17

Max Range: 1.4884. Min Range: -1.4884

Max Act: 0.7242. Min Act: -0.0000

Data Index: 1466117 (The Pile)

Max Activating Token Index: 560

Text #18

Max Range: 1.4884. Min Range: -1.4884

Max Act: 0.6433. Min Act: -0.0000

Data Index: 669978 (The Pile)

Max Activating Token Index: 359

Text #19

Max Range: 1.4884. Min Range: -1.4884

Max Act: 0.6171. Min Act: -0.0000

Data Index: 1735275 (The Pile)

Max Activating Token Index: 657