Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 70 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.4226. Min Range: -1.4226

Max Act: 1.4226. Min Act: -0.0001

Data Index: 823828 (C4 (Web Text))

Max Activating Token Index: 212

Text #1

Max Range: 1.4226. Min Range: -1.4226

Max Act: 1.2104. Min Act: -0.0001

Data Index: 1159245 (C4 (Web Text))

Max Activating Token Index: 86

Text #2

Max Range: 1.4226. Min Range: -1.4226

Max Act: 1.1409. Min Act: -0.0001

Data Index: 426747 (C4 (Web Text))

Max Activating Token Index: 887

Text #3

Max Range: 1.4226. Min Range: -1.4226

Max Act: 1.2058. Min Act: -0.0001

Data Index: 100539 (C4 (Web Text))

Max Activating Token Index: 975

Text #4

Max Range: 1.4226. Min Range: -1.4226

Max Act: 1.1802. Min Act: -0.0001

Data Index: 666701 (C4 (Web Text))

Max Activating Token Index: 676

Text #5

Max Range: 1.4226. Min Range: -1.4226

Max Act: 1.1584. Min Act: -0.0001

Data Index: 1008936 (C4 (Web Text))

Max Activating Token Index: 364

Text #6

Max Range: 1.4226. Min Range: -1.4226

Max Act: 1.0500. Min Act: -0.0001

Data Index: 219502 (C4 (Web Text))

Max Activating Token Index: 238

Text #7

Max Range: 1.4226. Min Range: -1.4226

Max Act: 1.0670. Min Act: -0.0001

Data Index: 563663 (C4 (Web Text))

Max Activating Token Index: 72

Text #8

Max Range: 1.4226. Min Range: -1.4226

Max Act: 0.9942. Min Act: -0.0001

Data Index: 1151410 (C4 (Web Text))

Max Activating Token Index: 329

Text #9

Max Range: 1.4226. Min Range: -1.4226

Max Act: 1.0393. Min Act: -0.0001

Data Index: 1273658 (C4 (Web Text))

Max Activating Token Index: 559

Text #10

Max Range: 1.4226. Min Range: -1.4226

Max Act: 0.9744. Min Act: -0.0001

Data Index: 631233 (C4 (Web Text))

Max Activating Token Index: 380

Text #11

Max Range: 1.4226. Min Range: -1.4226

Max Act: 1.0033. Min Act: -0.0001

Data Index: 232044 (C4 (Web Text))

Max Activating Token Index: 46

Text #12

Max Range: 1.4226. Min Range: -1.4226

Max Act: 1.0519. Min Act: -0.0001

Data Index: 397477 (C4 (Web Text))

Max Activating Token Index: 81

Text #13

Max Range: 1.4226. Min Range: -1.4226

Max Act: 1.0106. Min Act: -0.0001

Data Index: 966978 (C4 (Web Text))

Max Activating Token Index: 9

Text #14

Max Range: 1.4226. Min Range: -1.4226

Max Act: 1.0050. Min Act: -0.0001

Data Index: 793779 (C4 (Web Text))

Max Activating Token Index: 52

Text #15

Max Range: 1.4226. Min Range: -1.4226

Max Act: 1.0270. Min Act: -0.0001

Data Index: 1148648 (C4 (Web Text))

Max Activating Token Index: 260

Text #16

Max Range: 1.4226. Min Range: -1.4226

Max Act: 0.9296. Min Act: -0.0001

Data Index: 356377 (C4 (Web Text))

Max Activating Token Index: 28

Text #17

Max Range: 1.4226. Min Range: -1.4226

Max Act: 0.9847. Min Act: -0.0001

Data Index: 409426 (C4 (Web Text))

Max Activating Token Index: 578

Text #18

Max Range: 1.4226. Min Range: -1.4226

Max Act: 0.9838. Min Act: -0.0001

Data Index: 918540 (C4 (Web Text))

Max Activating Token Index: 679

Text #19

Max Range: 1.4226. Min Range: -1.4226

Max Act: 0.9252. Min Act: -0.0001

Data Index: 1227171 (C4 (Web Text))

Max Activating Token Index: 53