Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3844 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.6114. Min Range: -0.6114

Max Act: 0.6114. Min Act: -0.0000

Data Index: 1040247 (C4 (Web Text))

Max Activating Token Index: 183

Text #1

Max Range: 0.6114. Min Range: -0.6114

Max Act: 0.5975. Min Act: -0.0000

Data Index: 167612 (C4 (Web Text))

Max Activating Token Index: 92

Text #2

Max Range: 0.6114. Min Range: -0.6114

Max Act: 0.5968. Min Act: -0.0000

Data Index: 766548 (C4 (Web Text))

Max Activating Token Index: 432

Text #3

Max Range: 0.6114. Min Range: -0.6114

Max Act: 0.5702. Min Act: -0.0000

Data Index: 1173374 (C4 (Web Text))

Max Activating Token Index: 672

Text #4

Max Range: 0.6114. Min Range: -0.6114

Max Act: 0.5840. Min Act: 0.0000

Data Index: 1056852 (C4 (Web Text))

Max Activating Token Index: 81

Text #5

Max Range: 0.6114. Min Range: -0.6114

Max Act: 0.5606. Min Act: -0.0000

Data Index: 15836 (C4 (Web Text))

Max Activating Token Index: 160

Text #6

Max Range: 0.6114. Min Range: -0.6114

Max Act: 0.5470. Min Act: -0.0000

Data Index: 533148 (C4 (Web Text))

Max Activating Token Index: 701

Text #7

Max Range: 0.6114. Min Range: -0.6114

Max Act: 0.5557. Min Act: 0.0000

Data Index: 1244987 (C4 (Web Text))

Max Activating Token Index: 508

Text #8

Max Range: 0.6114. Min Range: -0.6114

Max Act: 0.5685. Min Act: -0.0000

Data Index: 14221 (C4 (Web Text))

Max Activating Token Index: 273

Text #9

Max Range: 0.6114. Min Range: -0.6114

Max Act: 0.5257. Min Act: -0.0000

Data Index: 711633 (C4 (Web Text))

Max Activating Token Index: 971

Text #10

Max Range: 0.6114. Min Range: -0.6114

Max Act: 0.5243. Min Act: -0.0000

Data Index: 1004395 (C4 (Web Text))

Max Activating Token Index: 924

Text #11

Max Range: 0.6114. Min Range: -0.6114

Max Act: 0.5173. Min Act: -0.0000

Data Index: 1508202 (Python Code)

Max Activating Token Index: 577

Text #12

Max Range: 0.6114. Min Range: -0.6114

Max Act: 0.4990. Min Act: -0.0000

Data Index: 374498 (C4 (Web Text))

Max Activating Token Index: 143

Text #13

Max Range: 0.6114. Min Range: -0.6114

Max Act: 0.5130. Min Act: 0.0000

Data Index: 244420 (C4 (Web Text))

Max Activating Token Index: 870

Text #14

Max Range: 0.6114. Min Range: -0.6114

Max Act: 0.5256. Min Act: -0.0000

Data Index: 923744 (C4 (Web Text))

Max Activating Token Index: 423

Text #15

Max Range: 0.6114. Min Range: -0.6114

Max Act: 0.5045. Min Act: -0.0000

Data Index: 1003018 (C4 (Web Text))

Max Activating Token Index: 495

Text #16

Max Range: 0.6114. Min Range: -0.6114

Max Act: 0.5050. Min Act: -0.0000

Data Index: 399329 (C4 (Web Text))

Max Activating Token Index: 532

Text #17

Max Range: 0.6114. Min Range: -0.6114

Max Act: 0.4996. Min Act: -0.0000

Data Index: 1292751 (C4 (Web Text))

Max Activating Token Index: 115

Text #18

Max Range: 0.6114. Min Range: -0.6114

Max Act: 0.4962. Min Act: -0.0000

Data Index: 346192 (C4 (Web Text))

Max Activating Token Index: 119

Text #19

Max Range: 0.6114. Min Range: -0.6114

Max Act: 0.4941. Min Act: -0.0000

Data Index: 1158622 (C4 (Web Text))

Max Activating Token Index: 484