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

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

Neuron 3561 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5173. Min Range: -0.5173

Max Act: 0.5173. Min Act: -0.0001

Data Index: 95518 (C4 (Web Text))

Max Activating Token Index: 236

Text #1

Max Range: 0.5173. Min Range: -0.5173

Max Act: 0.4495. Min Act: -0.0001

Data Index: 294366 (C4 (Web Text))

Max Activating Token Index: 119

Text #2

Max Range: 0.5173. Min Range: -0.5173

Max Act: 0.3747. Min Act: -0.0000

Data Index: 735658 (C4 (Web Text))

Max Activating Token Index: 776

Text #3

Max Range: 0.5173. Min Range: -0.5173

Max Act: 0.3554. Min Act: -0.0001

Data Index: 136605 (C4 (Web Text))

Max Activating Token Index: 151

Text #4

Max Range: 0.5173. Min Range: -0.5173

Max Act: 0.3672. Min Act: -0.0001

Data Index: 1202435 (C4 (Web Text))

Max Activating Token Index: 241

Text #5

Max Range: 0.5173. Min Range: -0.5173

Max Act: 0.3482. Min Act: -0.0000

Data Index: 384735 (C4 (Web Text))

Max Activating Token Index: 534

Text #6

Max Range: 0.5173. Min Range: -0.5173

Max Act: 0.3430. Min Act: -0.0001

Data Index: 286735 (C4 (Web Text))

Max Activating Token Index: 186

Text #7

Max Range: 0.5173. Min Range: -0.5173

Max Act: 0.3520. Min Act: -0.0001

Data Index: 863121 (C4 (Web Text))

Max Activating Token Index: 120

Text #8

Max Range: 0.5173. Min Range: -0.5173

Max Act: 0.3378. Min Act: -0.0001

Data Index: 1140818 (C4 (Web Text))

Max Activating Token Index: 561

Text #9

Max Range: 0.5173. Min Range: -0.5173

Max Act: 0.3493. Min Act: -0.0000

Data Index: 724459 (C4 (Web Text))

Max Activating Token Index: 277

Text #10

Max Range: 0.5173. Min Range: -0.5173

Max Act: 0.3605. Min Act: -0.0001

Data Index: 205419 (C4 (Web Text))

Max Activating Token Index: 313

Text #11

Max Range: 0.5173. Min Range: -0.5173

Max Act: 0.3375. Min Act: -0.0001

Data Index: 1224000 (C4 (Web Text))

Max Activating Token Index: 694

Text #12

Max Range: 0.5173. Min Range: -0.5173

Max Act: 0.3334. Min Act: -0.0001

Data Index: 292920 (C4 (Web Text))

Max Activating Token Index: 134

Text #13

Max Range: 0.5173. Min Range: -0.5173

Max Act: 0.3350. Min Act: -0.0001

Data Index: 694930 (C4 (Web Text))

Max Activating Token Index: 373

Text #14

Max Range: 0.5173. Min Range: -0.5173

Max Act: 0.3191. Min Act: -0.0001

Data Index: 98701 (C4 (Web Text))

Max Activating Token Index: 580

Text #15

Max Range: 0.5173. Min Range: -0.5173

Max Act: 0.3144. Min Act: -0.0001

Data Index: 1057997 (C4 (Web Text))

Max Activating Token Index: 704

Text #16

Max Range: 0.5173. Min Range: -0.5173

Max Act: 0.3223. Min Act: -0.0000

Data Index: 143788 (C4 (Web Text))

Max Activating Token Index: 816

Text #17

Max Range: 0.5173. Min Range: -0.5173

Max Act: 0.2812. Min Act: -0.0000

Data Index: 463212 (C4 (Web Text))

Max Activating Token Index: 329

Text #18

Max Range: 0.5173. Min Range: -0.5173

Max Act: 0.3094. Min Act: -0.0001

Data Index: 653466 (C4 (Web Text))

Max Activating Token Index: 1022

Text #19

Max Range: 0.5173. Min Range: -0.5173

Max Act: 0.3216. Min Act: -0.0001

Data Index: 902635 (C4 (Web Text))

Max Activating Token Index: 357