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

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

Neuron 1083 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0815. Min Range: -1.0815

Max Act: 1.0815. Min Act: -0.0000

Data Index: 44596 (C4 (Web Text))

Max Activating Token Index: 884

Text #1

Max Range: 1.0815. Min Range: -1.0815

Max Act: 0.9946. Min Act: -0.0000

Data Index: 1222976 (C4 (Web Text))

Max Activating Token Index: 74

Text #2

Max Range: 1.0815. Min Range: -1.0815

Max Act: 1.0362. Min Act: -0.0000

Data Index: 232786 (C4 (Web Text))

Max Activating Token Index: 642

Text #3

Max Range: 1.0815. Min Range: -1.0815

Max Act: 0.9935. Min Act: -0.0000

Data Index: 1103763 (C4 (Web Text))

Max Activating Token Index: 730

Text #4

Max Range: 1.0815. Min Range: -1.0815

Max Act: 1.0280. Min Act: -0.0000

Data Index: 880771 (C4 (Web Text))

Max Activating Token Index: 913

Text #5

Max Range: 1.0815. Min Range: -1.0815

Max Act: 1.0092. Min Act: -0.0000

Data Index: 122562 (C4 (Web Text))

Max Activating Token Index: 802

Text #6

Max Range: 1.0815. Min Range: -1.0815

Max Act: 0.8645. Min Act: -0.0000

Data Index: 437239 (C4 (Web Text))

Max Activating Token Index: 610

Text #7

Max Range: 1.0815. Min Range: -1.0815

Max Act: 0.8484. Min Act: -0.0001

Data Index: 756148 (C4 (Web Text))

Max Activating Token Index: 239

Text #8

Max Range: 1.0815. Min Range: -1.0815

Max Act: 0.8290. Min Act: -0.0000

Data Index: 517582 (C4 (Web Text))

Max Activating Token Index: 922

Text #9

Max Range: 1.0815. Min Range: -1.0815

Max Act: 0.8364. Min Act: -0.0000

Data Index: 836046 (C4 (Web Text))

Max Activating Token Index: 470

Text #10

Max Range: 1.0815. Min Range: -1.0815

Max Act: 0.8676. Min Act: -0.0000

Data Index: 557712 (C4 (Web Text))

Max Activating Token Index: 200

Text #11

Max Range: 1.0815. Min Range: -1.0815

Max Act: 0.7976. Min Act: -0.0000

Data Index: 889183 (C4 (Web Text))

Max Activating Token Index: 823

Text #12

Max Range: 1.0815. Min Range: -1.0815

Max Act: 0.8381. Min Act: -0.0000

Data Index: 576975 (C4 (Web Text))

Max Activating Token Index: 922

Text #13

Max Range: 1.0815. Min Range: -1.0815

Max Act: 0.8352. Min Act: -0.0000

Data Index: 1271173 (C4 (Web Text))

Max Activating Token Index: 889

Text #14

Max Range: 1.0815. Min Range: -1.0815

Max Act: 0.7600. Min Act: -0.0000

Data Index: 897174 (C4 (Web Text))

Max Activating Token Index: 186

Text #15

Max Range: 1.0815. Min Range: -1.0815

Max Act: 0.7620. Min Act: -0.0000

Data Index: 964740 (C4 (Web Text))

Max Activating Token Index: 658

Text #16

Max Range: 1.0815. Min Range: -1.0815

Max Act: 0.7738. Min Act: -0.0000

Data Index: 386371 (C4 (Web Text))

Max Activating Token Index: 499

Text #17

Max Range: 1.0815. Min Range: -1.0815

Max Act: 0.7856. Min Act: -0.0000

Data Index: 1145578 (C4 (Web Text))

Max Activating Token Index: 818

Text #18

Max Range: 1.0815. Min Range: -1.0815

Max Act: 0.7848. Min Act: -0.0000

Data Index: 714329 (C4 (Web Text))

Max Activating Token Index: 255

Text #19

Max Range: 1.0815. Min Range: -1.0815

Max Act: 0.7459. Min Act: -0.0000

Data Index: 1271258 (C4 (Web Text))

Max Activating Token Index: 1019