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

Dataset: The Pile

Neuron 757 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: 0.4165. Min Range: -0.4165

Max Act: 0.4081. Min Act: -0.0000

Data Index: 569924 (The Pile)

Max Activating Token Index: 525

Text #1

Max Range: 0.4165. Min Range: -0.4165

Max Act: 0.4165. Min Act: -0.0000

Data Index: 636388 (The Pile)

Max Activating Token Index: 898

Text #2

Max Range: 0.4165. Min Range: -0.4165

Max Act: 0.3638. Min Act: -0.0000

Data Index: 984290 (The Pile)

Max Activating Token Index: 571

Text #3

Max Range: 0.4165. Min Range: -0.4165

Max Act: 0.3476. Min Act: -0.0000

Data Index: 1928111 (The Pile)

Max Activating Token Index: 1002

Text #4

Max Range: 0.4165. Min Range: -0.4165

Max Act: 0.3556. Min Act: -0.0000

Data Index: 973564 (The Pile)

Max Activating Token Index: 201

Text #5

Max Range: 0.4165. Min Range: -0.4165

Max Act: 0.3375. Min Act: -0.0000

Data Index: 924334 (The Pile)

Max Activating Token Index: 54

Text #6

Max Range: 0.4165. Min Range: -0.4165

Max Act: 0.2905. Min Act: -0.0000

Data Index: 1930886 (The Pile)

Max Activating Token Index: 137

Text #7

Max Range: 0.4165. Min Range: -0.4165

Max Act: 0.3269. Min Act: -0.0000

Data Index: 144619 (The Pile)

Max Activating Token Index: 990

Text #8

Max Range: 0.4165. Min Range: -0.4165

Max Act: 0.2924. Min Act: -0.0000

Data Index: 1402001 (The Pile)

Max Activating Token Index: 912

Text #9

Max Range: 0.4165. Min Range: -0.4165

Max Act: 0.2938. Min Act: -0.0000

Data Index: 1934583 (The Pile)

Max Activating Token Index: 914

Text #10

Max Range: 0.4165. Min Range: -0.4165

Max Act: 0.3070. Min Act: -0.0000

Data Index: 20908 (The Pile)

Max Activating Token Index: 657

Text #11

Max Range: 0.4165. Min Range: -0.4165

Max Act: 0.3091. Min Act: -0.0000

Data Index: 841651 (The Pile)

Max Activating Token Index: 351

Text #12

Max Range: 0.4165. Min Range: -0.4165

Max Act: 0.3164. Min Act: -0.0000

Data Index: 370414 (The Pile)

Max Activating Token Index: 668

Text #13

Max Range: 0.4165. Min Range: -0.4165

Max Act: 0.3263. Min Act: -0.0000

Data Index: 410110 (The Pile)

Max Activating Token Index: 601

Text #14

Max Range: 0.4165. Min Range: -0.4165

Max Act: 0.3202. Min Act: -0.0000

Data Index: 1985109 (The Pile)

Max Activating Token Index: 27

Text #15

Max Range: 0.4165. Min Range: -0.4165

Max Act: 0.3280. Min Act: -0.0000

Data Index: 1375274 (The Pile)

Max Activating Token Index: 886

Text #16

Max Range: 0.4165. Min Range: -0.4165

Max Act: 0.2943. Min Act: -0.0000

Data Index: 47870 (The Pile)

Max Activating Token Index: 294

Text #17

Max Range: 0.4165. Min Range: -0.4165

Max Act: 0.3178. Min Act: -0.0000

Data Index: 510123 (The Pile)

Max Activating Token Index: 998

Text #18

Max Range: 0.4165. Min Range: -0.4165

Max Act: 0.2963. Min Act: -0.0000

Data Index: 1153286 (The Pile)

Max Activating Token Index: 937

Text #19

Max Range: 0.4165. Min Range: -0.4165

Max Act: 0.2888. Min Act: -0.0000

Data Index: 634114 (The Pile)

Max Activating Token Index: 264