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

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

Neuron 1211 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6296. Min Range: -1.6296

Max Act: 1.6296. Min Act: -0.0000

Data Index: 1319128 (C4 (Web Text))

Max Activating Token Index: 970

Text #1

Max Range: 1.6296. Min Range: -1.6296

Max Act: 1.0979. Min Act: -0.0000

Data Index: 707078 (C4 (Web Text))

Max Activating Token Index: 880

Text #2

Max Range: 1.6296. Min Range: -1.6296

Max Act: 1.1986. Min Act: -0.0000

Data Index: 452855 (C4 (Web Text))

Max Activating Token Index: 223

Text #3

Max Range: 1.6296. Min Range: -1.6296

Max Act: 1.0920. Min Act: -0.0000

Data Index: 908469 (C4 (Web Text))

Max Activating Token Index: 649

Text #4

Max Range: 1.6296. Min Range: -1.6296

Max Act: 1.0721. Min Act: -0.0000

Data Index: 1213586 (C4 (Web Text))

Max Activating Token Index: 963

Text #5

Max Range: 1.6296. Min Range: -1.6296

Max Act: 0.9928. Min Act: -0.0000

Data Index: 1312556 (C4 (Web Text))

Max Activating Token Index: 475

Text #6

Max Range: 1.6296. Min Range: -1.6296

Max Act: 0.9908. Min Act: -0.0000

Data Index: 527402 (C4 (Web Text))

Max Activating Token Index: 892

Text #7

Max Range: 1.6296. Min Range: -1.6296

Max Act: 0.9100. Min Act: -0.0000

Data Index: 1115972 (C4 (Web Text))

Max Activating Token Index: 45

Text #8

Max Range: 1.6296. Min Range: -1.6296

Max Act: 0.9052. Min Act: -0.0000

Data Index: 1113985 (C4 (Web Text))

Max Activating Token Index: 327

Text #9

Max Range: 1.6296. Min Range: -1.6296

Max Act: 0.9474. Min Act: -0.0000

Data Index: 1291309 (C4 (Web Text))

Max Activating Token Index: 274

Text #10

Max Range: 1.6296. Min Range: -1.6296

Max Act: 0.9446. Min Act: -0.0000

Data Index: 135098 (C4 (Web Text))

Max Activating Token Index: 533

Text #11

Max Range: 1.6296. Min Range: -1.6296

Max Act: 0.9258. Min Act: -0.0000

Data Index: 145785 (C4 (Web Text))

Max Activating Token Index: 735

Text #12

Max Range: 1.6296. Min Range: -1.6296

Max Act: 0.9279. Min Act: -0.0000

Data Index: 1059533 (C4 (Web Text))

Max Activating Token Index: 372

Text #13

Max Range: 1.6296. Min Range: -1.6296

Max Act: 0.9193. Min Act: -0.0000

Data Index: 1076716 (C4 (Web Text))

Max Activating Token Index: 631

Text #14

Max Range: 1.6296. Min Range: -1.6296

Max Act: 0.8878. Min Act: -0.0000

Data Index: 317874 (C4 (Web Text))

Max Activating Token Index: 131

Text #15

Max Range: 1.6296. Min Range: -1.6296

Max Act: 0.8404. Min Act: -0.0000

Data Index: 981184 (C4 (Web Text))

Max Activating Token Index: 932

Text #16

Max Range: 1.6296. Min Range: -1.6296

Max Act: 0.8289. Min Act: -0.0000

Data Index: 1337571 (C4 (Web Text))

Max Activating Token Index: 98

Text #17

Max Range: 1.6296. Min Range: -1.6296

Max Act: 0.8282. Min Act: -0.0000

Data Index: 563756 (C4 (Web Text))

Max Activating Token Index: 1003

Text #18

Max Range: 1.6296. Min Range: -1.6296

Max Act: 0.8285. Min Act: -0.0000

Data Index: 25821 (C4 (Web Text))

Max Activating Token Index: 479

Text #19

Max Range: 1.6296. Min Range: -1.6296

Max Act: 0.7997. Min Act: -0.0000

Data Index: 1026349 (C4 (Web Text))

Max Activating Token Index: 631