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

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

Neuron 521 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8385. Min Range: -0.8385

Max Act: 0.8385. Min Act: -0.0001

Data Index: 453534 (C4 (Web Text))

Max Activating Token Index: 121

Text #1

Max Range: 0.8385. Min Range: -0.8385

Max Act: 0.7857. Min Act: -0.0001

Data Index: 176107 (C4 (Web Text))

Max Activating Token Index: 776

Text #2

Max Range: 0.8385. Min Range: -0.8385

Max Act: 0.7823. Min Act: -0.0001

Data Index: 87708 (C4 (Web Text))

Max Activating Token Index: 453

Text #3

Max Range: 0.8385. Min Range: -0.8385

Max Act: 0.7911. Min Act: -0.0001

Data Index: 834633 (C4 (Web Text))

Max Activating Token Index: 725

Text #4

Max Range: 0.8385. Min Range: -0.8385

Max Act: 0.7669. Min Act: -0.0001

Data Index: 1092948 (C4 (Web Text))

Max Activating Token Index: 60

Text #5

Max Range: 0.8385. Min Range: -0.8385

Max Act: 0.7311. Min Act: -0.0001

Data Index: 928583 (C4 (Web Text))

Max Activating Token Index: 240

Text #6

Max Range: 0.8385. Min Range: -0.8385

Max Act: 0.7197. Min Act: -0.0001

Data Index: 1226923 (C4 (Web Text))

Max Activating Token Index: 485

Text #7

Max Range: 0.8385. Min Range: -0.8385

Max Act: 0.7180. Min Act: -0.0000

Data Index: 226942 (C4 (Web Text))

Max Activating Token Index: 195

Text #8

Max Range: 0.8385. Min Range: -0.8385

Max Act: 0.7011. Min Act: -0.0001

Data Index: 218 (C4 (Web Text))

Max Activating Token Index: 948

Text #9

Max Range: 0.8385. Min Range: -0.8385

Max Act: 0.6788. Min Act: -0.0001

Data Index: 518267 (C4 (Web Text))

Max Activating Token Index: 782

Text #10

Max Range: 0.8385. Min Range: -0.8385

Max Act: 0.6481. Min Act: -0.0001

Data Index: 950873 (C4 (Web Text))

Max Activating Token Index: 917

Text #11

Max Range: 0.8385. Min Range: -0.8385

Max Act: 0.6756. Min Act: -0.0001

Data Index: 876187 (C4 (Web Text))

Max Activating Token Index: 752

Text #12

Max Range: 0.8385. Min Range: -0.8385

Max Act: 0.6335. Min Act: -0.0001

Data Index: 1172191 (C4 (Web Text))

Max Activating Token Index: 611

Text #13

Max Range: 0.8385. Min Range: -0.8385

Max Act: 0.6190. Min Act: -0.0001

Data Index: 1263546 (C4 (Web Text))

Max Activating Token Index: 988

Text #14

Max Range: 0.8385. Min Range: -0.8385

Max Act: 0.6193. Min Act: -0.0001

Data Index: 771350 (C4 (Web Text))

Max Activating Token Index: 2

Text #15

Max Range: 0.8385. Min Range: -0.8385

Max Act: 0.6193. Min Act: -0.0001

Data Index: 349583 (C4 (Web Text))

Max Activating Token Index: 2

Text #16

Max Range: 0.8385. Min Range: -0.8385

Max Act: 0.6522. Min Act: -0.0001

Data Index: 1046286 (C4 (Web Text))

Max Activating Token Index: 308

Text #17

Max Range: 0.8385. Min Range: -0.8385

Max Act: 0.6470. Min Act: -0.0001

Data Index: 374907 (C4 (Web Text))

Max Activating Token Index: 332

Text #18

Max Range: 0.8385. Min Range: -0.8385

Max Act: 0.6304. Min Act: -0.0001

Data Index: 479791 (C4 (Web Text))

Max Activating Token Index: 464

Text #19

Max Range: 0.8385. Min Range: -0.8385

Max Act: 0.6072. Min Act: -0.0001

Data Index: 872387 (C4 (Web Text))

Max Activating Token Index: 583