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

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

Neuron 434 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: 0.4857. Min Range: -0.4857

Max Act: 0.4857. Min Act: -0.0000

Data Index: 353461 (C4 (Web Text))

Max Activating Token Index: 1003

Text #1

Max Range: 0.4857. Min Range: -0.4857

Max Act: 0.4161. Min Act: -0.0001

Data Index: 961905 (C4 (Web Text))

Max Activating Token Index: 407

Text #2

Max Range: 0.4857. Min Range: -0.4857

Max Act: 0.4133. Min Act: -0.0000

Data Index: 1255968 (C4 (Web Text))

Max Activating Token Index: 958

Text #3

Max Range: 0.4857. Min Range: -0.4857

Max Act: 0.3321. Min Act: -0.0000

Data Index: 675196 (C4 (Web Text))

Max Activating Token Index: 958

Text #4

Max Range: 0.4857. Min Range: -0.4857

Max Act: 0.3284. Min Act: -0.0001

Data Index: 152992 (C4 (Web Text))

Max Activating Token Index: 319

Text #5

Max Range: 0.4857. Min Range: -0.4857

Max Act: 0.3198. Min Act: -0.0000

Data Index: 804859 (C4 (Web Text))

Max Activating Token Index: 686

Text #6

Max Range: 0.4857. Min Range: -0.4857

Max Act: 0.3047. Min Act: -0.0000

Data Index: 574395 (C4 (Web Text))

Max Activating Token Index: 867

Text #7

Max Range: 0.4857. Min Range: -0.4857

Max Act: 0.2777. Min Act: -0.0001

Data Index: 110367 (C4 (Web Text))

Max Activating Token Index: 82

Text #8

Max Range: 0.4857. Min Range: -0.4857

Max Act: 0.2766. Min Act: -0.0001

Data Index: 597111 (C4 (Web Text))

Max Activating Token Index: 930

Text #9

Max Range: 0.4857. Min Range: -0.4857

Max Act: 0.2743. Min Act: -0.0001

Data Index: 1315823 (C4 (Web Text))

Max Activating Token Index: 173

Text #10

Max Range: 0.4857. Min Range: -0.4857

Max Act: 0.2752. Min Act: -0.0000

Data Index: 252474 (C4 (Web Text))

Max Activating Token Index: 362

Text #11

Max Range: 0.4857. Min Range: -0.4857

Max Act: 0.2639. Min Act: -0.0001

Data Index: 150141 (C4 (Web Text))

Max Activating Token Index: 662

Text #12

Max Range: 0.4857. Min Range: -0.4857

Max Act: 0.2684. Min Act: -0.0001

Data Index: 44091 (C4 (Web Text))

Max Activating Token Index: 149

Text #13

Max Range: 0.4857. Min Range: -0.4857

Max Act: 0.2524. Min Act: -0.0001

Data Index: 1079206 (C4 (Web Text))

Max Activating Token Index: 795

Text #14

Max Range: 0.4857. Min Range: -0.4857

Max Act: 0.2495. Min Act: -0.0000

Data Index: 1082873 (C4 (Web Text))

Max Activating Token Index: 453

Text #15

Max Range: 0.4857. Min Range: -0.4857

Max Act: 0.2437. Min Act: -0.0001

Data Index: 1183882 (C4 (Web Text))

Max Activating Token Index: 114

Text #16

Max Range: 0.4857. Min Range: -0.4857

Max Act: 0.2363. Min Act: -0.0000

Data Index: 85315 (C4 (Web Text))

Max Activating Token Index: 869

Text #17

Max Range: 0.4857. Min Range: -0.4857

Max Act: 0.2349. Min Act: -0.0000

Data Index: 613145 (C4 (Web Text))

Max Activating Token Index: 181

Text #18

Max Range: 0.4857. Min Range: -0.4857

Max Act: 0.2397. Min Act: -0.0001

Data Index: 406330 (C4 (Web Text))

Max Activating Token Index: 767

Text #19

Max Range: 0.4857. Min Range: -0.4857

Max Act: 0.2343. Min Act: -0.0001

Data Index: 47788 (C4 (Web Text))

Max Activating Token Index: 989