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

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

Neuron 5365 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5825. Min Range: -1.5825

Max Act: 1.5825. Min Act: -0.0000

Data Index: 113889 (C4 (Web Text))

Max Activating Token Index: 311

Text #1

Max Range: 1.5825. Min Range: -1.5825

Max Act: 1.4997. Min Act: -0.0000

Data Index: 823546 (C4 (Web Text))

Max Activating Token Index: 885

Text #2

Max Range: 1.5825. Min Range: -1.5825

Max Act: 1.4800. Min Act: -0.0001

Data Index: 1283928 (C4 (Web Text))

Max Activating Token Index: 44

Text #3

Max Range: 1.5825. Min Range: -1.5825

Max Act: 1.3887. Min Act: -0.0000

Data Index: 677016 (C4 (Web Text))

Max Activating Token Index: 511

Text #4

Max Range: 1.5825. Min Range: -1.5825

Max Act: 1.2831. Min Act: -0.0000

Data Index: 194818 (C4 (Web Text))

Max Activating Token Index: 991

Text #5

Max Range: 1.5825. Min Range: -1.5825

Max Act: 1.2288. Min Act: -0.0000

Data Index: 1001723 (C4 (Web Text))

Max Activating Token Index: 891

Text #6

Max Range: 1.5825. Min Range: -1.5825

Max Act: 1.1992. Min Act: -0.0000

Data Index: 898626 (C4 (Web Text))

Max Activating Token Index: 366

Text #7

Max Range: 1.5825. Min Range: -1.5825

Max Act: 1.2390. Min Act: -0.0000

Data Index: 1110394 (C4 (Web Text))

Max Activating Token Index: 32

Text #8

Max Range: 1.5825. Min Range: -1.5825

Max Act: 1.1945. Min Act: -0.0000

Data Index: 542582 (C4 (Web Text))

Max Activating Token Index: 958

Text #9

Max Range: 1.5825. Min Range: -1.5825

Max Act: 1.2331. Min Act: -0.0001

Data Index: 825810 (C4 (Web Text))

Max Activating Token Index: 970

Text #10

Max Range: 1.5825. Min Range: -1.5825

Max Act: 1.2479. Min Act: -0.0000

Data Index: 599880 (C4 (Web Text))

Max Activating Token Index: 98

Text #11

Max Range: 1.5825. Min Range: -1.5825

Max Act: 1.1704. Min Act: -0.0000

Data Index: 100481 (C4 (Web Text))

Max Activating Token Index: 997

Text #12

Max Range: 1.5825. Min Range: -1.5825

Max Act: 1.2135. Min Act: -0.0001

Data Index: 181495 (C4 (Web Text))

Max Activating Token Index: 727

Text #13

Max Range: 1.5825. Min Range: -1.5825

Max Act: 1.2326. Min Act: -0.0001

Data Index: 493659 (C4 (Web Text))

Max Activating Token Index: 616

Text #14

Max Range: 1.5825. Min Range: -1.5825

Max Act: 1.0932. Min Act: -0.0001

Data Index: 1206639 (C4 (Web Text))

Max Activating Token Index: 619

Text #15

Max Range: 1.5825. Min Range: -1.5825

Max Act: 1.1565. Min Act: -0.0000

Data Index: 549932 (C4 (Web Text))

Max Activating Token Index: 420

Text #16

Max Range: 1.5825. Min Range: -1.5825

Max Act: 1.0996. Min Act: -0.0000

Data Index: 662654 (C4 (Web Text))

Max Activating Token Index: 158

Text #17

Max Range: 1.5825. Min Range: -1.5825

Max Act: 1.1273. Min Act: -0.0000

Data Index: 509285 (C4 (Web Text))

Max Activating Token Index: 393

Text #18

Max Range: 1.5825. Min Range: -1.5825

Max Act: 1.1203. Min Act: -0.0000

Data Index: 329152 (C4 (Web Text))

Max Activating Token Index: 127

Text #19

Max Range: 1.5825. Min Range: -1.5825

Max Act: 1.0861. Min Act: -0.0001

Data Index: 1226913 (C4 (Web Text))

Max Activating Token Index: 611