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

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

Neuron 2140 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3407. Min Range: -1.3407

Max Act: 1.3407. Min Act: -0.0001

Data Index: 474766 (C4 (Web Text))

Max Activating Token Index: 634

Text #1

Max Range: 1.3407. Min Range: -1.3407

Max Act: 1.3159. Min Act: -0.0001

Data Index: 156836 (C4 (Web Text))

Max Activating Token Index: 649

Text #2

Max Range: 1.3407. Min Range: -1.3407

Max Act: 1.2714. Min Act: -0.0001

Data Index: 353820 (C4 (Web Text))

Max Activating Token Index: 1014

Text #3

Max Range: 1.3407. Min Range: -1.3407

Max Act: 1.2683. Min Act: -0.0001

Data Index: 810872 (C4 (Web Text))

Max Activating Token Index: 828

Text #4

Max Range: 1.3407. Min Range: -1.3407

Max Act: 1.2660. Min Act: -0.0001

Data Index: 802671 (C4 (Web Text))

Max Activating Token Index: 988

Text #5

Max Range: 1.3407. Min Range: -1.3407

Max Act: 1.2103. Min Act: -0.0001

Data Index: 987025 (C4 (Web Text))

Max Activating Token Index: 298

Text #6

Max Range: 1.3407. Min Range: -1.3407

Max Act: 1.2139. Min Act: -0.0001

Data Index: 215126 (C4 (Web Text))

Max Activating Token Index: 587

Text #7

Max Range: 1.3407. Min Range: -1.3407

Max Act: 1.2770. Min Act: -0.0001

Data Index: 999130 (C4 (Web Text))

Max Activating Token Index: 752

Text #8

Max Range: 1.3407. Min Range: -1.3407

Max Act: 1.2069. Min Act: -0.0001

Data Index: 1210281 (C4 (Web Text))

Max Activating Token Index: 406

Text #9

Max Range: 1.3407. Min Range: -1.3407

Max Act: 1.3164. Min Act: -0.0001

Data Index: 1087242 (C4 (Web Text))

Max Activating Token Index: 916

Text #10

Max Range: 1.3407. Min Range: -1.3407

Max Act: 1.2360. Min Act: -0.0001

Data Index: 786245 (C4 (Web Text))

Max Activating Token Index: 394

Text #11

Max Range: 1.3407. Min Range: -1.3407

Max Act: 1.2028. Min Act: -0.0001

Data Index: 1269845 (C4 (Web Text))

Max Activating Token Index: 618

Text #12

Max Range: 1.3407. Min Range: -1.3407

Max Act: 1.2175. Min Act: -0.0001

Data Index: 340620 (C4 (Web Text))

Max Activating Token Index: 677

Text #13

Max Range: 1.3407. Min Range: -1.3407

Max Act: 1.1906. Min Act: -0.0001

Data Index: 870920 (C4 (Web Text))

Max Activating Token Index: 802

Text #14

Max Range: 1.3407. Min Range: -1.3407

Max Act: 1.2193. Min Act: -0.0001

Data Index: 590968 (C4 (Web Text))

Max Activating Token Index: 836

Text #15

Max Range: 1.3407. Min Range: -1.3407

Max Act: 1.1799. Min Act: -0.0001

Data Index: 1275099 (C4 (Web Text))

Max Activating Token Index: 903

Text #16

Max Range: 1.3407. Min Range: -1.3407

Max Act: 1.2107. Min Act: -0.0001

Data Index: 876717 (C4 (Web Text))

Max Activating Token Index: 920

Text #17

Max Range: 1.3407. Min Range: -1.3407

Max Act: 1.1754. Min Act: -0.0001

Data Index: 493375 (C4 (Web Text))

Max Activating Token Index: 149

Text #18

Max Range: 1.3407. Min Range: -1.3407

Max Act: 1.1971. Min Act: -0.0001

Data Index: 287441 (C4 (Web Text))

Max Activating Token Index: 870

Text #19

Max Range: 1.3407. Min Range: -1.3407

Max Act: 1.1929. Min Act: -0.0001

Data Index: 1634387 (Python Code)

Max Activating Token Index: 1018