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

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

Neuron 4788 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.7242. Min Range: -8.7242

Max Act: 8.6548. Min Act: -0.0000

Data Index: 61169 (C4 (Web Text))

Max Activating Token Index: 62

Text #1

Max Range: 8.7242. Min Range: -8.7242

Max Act: 8.7242. Min Act: -0.0000

Data Index: 377103 (C4 (Web Text))

Max Activating Token Index: 181

Text #2

Max Range: 8.7242. Min Range: -8.7242

Max Act: 8.3373. Min Act: -0.0000

Data Index: 1026603 (C4 (Web Text))

Max Activating Token Index: 277

Text #3

Max Range: 8.7242. Min Range: -8.7242

Max Act: 8.1732. Min Act: -0.0000

Data Index: 920739 (C4 (Web Text))

Max Activating Token Index: 177

Text #4

Max Range: 8.7242. Min Range: -8.7242

Max Act: 8.0873. Min Act: -0.0000

Data Index: 610918 (C4 (Web Text))

Max Activating Token Index: 720

Text #5

Max Range: 8.7242. Min Range: -8.7242

Max Act: 8.0521. Min Act: -0.0000

Data Index: 1252743 (C4 (Web Text))

Max Activating Token Index: 498

Text #6

Max Range: 8.7242. Min Range: -8.7242

Max Act: 7.6079. Min Act: -0.0000

Data Index: 849002 (C4 (Web Text))

Max Activating Token Index: 602

Text #7

Max Range: 8.7242. Min Range: -8.7242

Max Act: 7.3643. Min Act: -0.0000

Data Index: 746929 (C4 (Web Text))

Max Activating Token Index: 318

Text #8

Max Range: 8.7242. Min Range: -8.7242

Max Act: 6.6742. Min Act: -0.0000

Data Index: 398869 (C4 (Web Text))

Max Activating Token Index: 614

Text #9

Max Range: 8.7242. Min Range: -8.7242

Max Act: 6.9628. Min Act: -0.0000

Data Index: 857132 (C4 (Web Text))

Max Activating Token Index: 438

Text #10

Max Range: 8.7242. Min Range: -8.7242

Max Act: 6.0398. Min Act: -0.0000

Data Index: 529767 (C4 (Web Text))

Max Activating Token Index: 668

Text #11

Max Range: 8.7242. Min Range: -8.7242

Max Act: 5.0450. Min Act: -0.0000

Data Index: 382528 (C4 (Web Text))

Max Activating Token Index: 187

Text #12

Max Range: 8.7242. Min Range: -8.7242

Max Act: 5.3435. Min Act: -0.0000

Data Index: 196427 (C4 (Web Text))

Max Activating Token Index: 539

Text #13

Max Range: 8.7242. Min Range: -8.7242

Max Act: 5.0694. Min Act: -0.0000

Data Index: 943481 (C4 (Web Text))

Max Activating Token Index: 840

Text #14

Max Range: 8.7242. Min Range: -8.7242

Max Act: 4.8419. Min Act: -0.0000

Data Index: 378531 (C4 (Web Text))

Max Activating Token Index: 829

Text #15

Max Range: 8.7242. Min Range: -8.7242

Max Act: 5.1183. Min Act: -0.0000

Data Index: 1350260 (C4 (Web Text))

Max Activating Token Index: 324

Text #16

Max Range: 8.7242. Min Range: -8.7242

Max Act: 5.0545. Min Act: -0.0000

Data Index: 951916 (C4 (Web Text))

Max Activating Token Index: 302

Text #17

Max Range: 8.7242. Min Range: -8.7242

Max Act: 5.0274. Min Act: -0.0000

Data Index: 938434 (C4 (Web Text))

Max Activating Token Index: 751

Text #18

Max Range: 8.7242. Min Range: -8.7242

Max Act: 4.9544. Min Act: -0.0000

Data Index: 416543 (C4 (Web Text))

Max Activating Token Index: 124

Text #19

Max Range: 8.7242. Min Range: -8.7242

Max Act: 4.9664. Min Act: -0.0000

Data Index: 677041 (C4 (Web Text))

Max Activating Token Index: 238