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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 485 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3413. Min Range: -0.3413

Max Act: 0.3413. Min Act: -0.0000

Data Index: 220585 (C4 (Web Text))

Max Activating Token Index: 201

Text #1

Max Range: 0.3413. Min Range: -0.3413

Max Act: 0.3185. Min Act: -0.0000

Data Index: 656516 (C4 (Web Text))

Max Activating Token Index: 669

Text #2

Max Range: 0.3413. Min Range: -0.3413

Max Act: 0.3239. Min Act: -0.0000

Data Index: 754760 (C4 (Web Text))

Max Activating Token Index: 898

Text #3

Max Range: 0.3413. Min Range: -0.3413

Max Act: 0.3231. Min Act: -0.0000

Data Index: 161833 (C4 (Web Text))

Max Activating Token Index: 483

Text #4

Max Range: 0.3413. Min Range: -0.3413

Max Act: 0.3174. Min Act: -0.0000

Data Index: 422987 (C4 (Web Text))

Max Activating Token Index: 334

Text #5

Max Range: 0.3413. Min Range: -0.3413

Max Act: 0.3268. Min Act: 0.0000

Data Index: 1000878 (C4 (Web Text))

Max Activating Token Index: 55

Text #6

Max Range: 0.3413. Min Range: -0.3413

Max Act: 0.2928. Min Act: -0.0000

Data Index: 165719 (C4 (Web Text))

Max Activating Token Index: 111

Text #7

Max Range: 0.3413. Min Range: -0.3413

Max Act: 0.3092. Min Act: -0.0000

Data Index: 1197736 (C4 (Web Text))

Max Activating Token Index: 453

Text #8

Max Range: 0.3413. Min Range: -0.3413

Max Act: 0.2984. Min Act: -0.0001

Data Index: 1121086 (C4 (Web Text))

Max Activating Token Index: 775

Text #9

Max Range: 0.3413. Min Range: -0.3413

Max Act: 0.2990. Min Act: -0.0000

Data Index: 575986 (C4 (Web Text))

Max Activating Token Index: 504

Text #10

Max Range: 0.3413. Min Range: -0.3413

Max Act: 0.2823. Min Act: -0.0000

Data Index: 446943 (C4 (Web Text))

Max Activating Token Index: 749

Text #11

Max Range: 0.3413. Min Range: -0.3413

Max Act: 0.2607. Min Act: 0.0001

Data Index: 10878 (C4 (Web Text))

Max Activating Token Index: 74

Text #12

Max Range: 0.3413. Min Range: -0.3413

Max Act: 0.2899. Min Act: -0.0000

Data Index: 742914 (C4 (Web Text))

Max Activating Token Index: 272

Text #13

Max Range: 0.3413. Min Range: -0.3413

Max Act: 0.2892. Min Act: -0.0001

Data Index: 132209 (C4 (Web Text))

Max Activating Token Index: 799

Text #14

Max Range: 0.3413. Min Range: -0.3413

Max Act: 0.3009. Min Act: -0.0000

Data Index: 490630 (C4 (Web Text))

Max Activating Token Index: 61

Text #15

Max Range: 0.3413. Min Range: -0.3413

Max Act: 0.2787. Min Act: -0.0000

Data Index: 613855 (C4 (Web Text))

Max Activating Token Index: 368

Text #16

Max Range: 0.3413. Min Range: -0.3413

Max Act: 0.2962. Min Act: -0.0000

Data Index: 1058954 (C4 (Web Text))

Max Activating Token Index: 622

Text #17

Max Range: 0.3413. Min Range: -0.3413

Max Act: 0.2859. Min Act: -0.0000

Data Index: 591718 (C4 (Web Text))

Max Activating Token Index: 453

Text #18

Max Range: 0.3413. Min Range: -0.3413

Max Act: 0.2856. Min Act: -0.0001

Data Index: 1329120 (C4 (Web Text))

Max Activating Token Index: 973

Text #19

Max Range: 0.3413. Min Range: -0.3413

Max Act: 0.2959. Min Act: -0.0000

Data Index: 330296 (C4 (Web Text))

Max Activating Token Index: 685