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

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

Neuron 3286 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: 5.8246. Min Range: -5.8246

Max Act: 5.8246. Min Act: -0.0000

Data Index: 294286 (C4 (Web Text))

Max Activating Token Index: 37

Text #1

Max Range: 5.8246. Min Range: -5.8246

Max Act: 5.1346. Min Act: -0.0000

Data Index: 472476 (C4 (Web Text))

Max Activating Token Index: 768

Text #2

Max Range: 5.8246. Min Range: -5.8246

Max Act: 5.3559. Min Act: -0.0000

Data Index: 367306 (C4 (Web Text))

Max Activating Token Index: 723

Text #3

Max Range: 5.8246. Min Range: -5.8246

Max Act: 5.0145. Min Act: -0.0000

Data Index: 145854 (C4 (Web Text))

Max Activating Token Index: 842

Text #4

Max Range: 5.8246. Min Range: -5.8246

Max Act: 4.5439. Min Act: -0.0000

Data Index: 1027130 (C4 (Web Text))

Max Activating Token Index: 839

Text #5

Max Range: 5.8246. Min Range: -5.8246

Max Act: 4.6738. Min Act: -0.0000

Data Index: 1305426 (C4 (Web Text))

Max Activating Token Index: 876

Text #6

Max Range: 5.8246. Min Range: -5.8246

Max Act: 4.2256. Min Act: -0.0000

Data Index: 1247622 (C4 (Web Text))

Max Activating Token Index: 76

Text #7

Max Range: 5.8246. Min Range: -5.8246

Max Act: 4.3165. Min Act: -0.0000

Data Index: 75226 (C4 (Web Text))

Max Activating Token Index: 577

Text #8

Max Range: 5.8246. Min Range: -5.8246

Max Act: 4.2152. Min Act: -0.0000

Data Index: 367641 (C4 (Web Text))

Max Activating Token Index: 361

Text #9

Max Range: 5.8246. Min Range: -5.8246

Max Act: 4.2005. Min Act: -0.0000

Data Index: 370360 (C4 (Web Text))

Max Activating Token Index: 18

Text #10

Max Range: 5.8246. Min Range: -5.8246

Max Act: 4.2184. Min Act: -0.0000

Data Index: 344462 (C4 (Web Text))

Max Activating Token Index: 476

Text #11

Max Range: 5.8246. Min Range: -5.8246

Max Act: 4.3604. Min Act: -0.0000

Data Index: 47591 (C4 (Web Text))

Max Activating Token Index: 175

Text #12

Max Range: 5.8246. Min Range: -5.8246

Max Act: 4.0894. Min Act: -0.0000

Data Index: 927045 (C4 (Web Text))

Max Activating Token Index: 93

Text #13

Max Range: 5.8246. Min Range: -5.8246

Max Act: 4.0653. Min Act: -0.0000

Data Index: 1023363 (C4 (Web Text))

Max Activating Token Index: 990

Text #14

Max Range: 5.8246. Min Range: -5.8246

Max Act: 4.0539. Min Act: -0.0000

Data Index: 253426 (C4 (Web Text))

Max Activating Token Index: 61

Text #15

Max Range: 5.8246. Min Range: -5.8246

Max Act: 4.1620. Min Act: -0.0000

Data Index: 478019 (C4 (Web Text))

Max Activating Token Index: 556

Text #16

Max Range: 5.8246. Min Range: -5.8246

Max Act: 4.0380. Min Act: -0.0000

Data Index: 554528 (C4 (Web Text))

Max Activating Token Index: 99

Text #17

Max Range: 5.8246. Min Range: -5.8246

Max Act: 3.9625. Min Act: -0.0000

Data Index: 642039 (C4 (Web Text))

Max Activating Token Index: 726

Text #18

Max Range: 5.8246. Min Range: -5.8246

Max Act: 3.9226. Min Act: -0.0000

Data Index: 450806 (C4 (Web Text))

Max Activating Token Index: 124

Text #19

Max Range: 5.8246. Min Range: -5.8246

Max Act: 3.7032. Min Act: -0.0000

Data Index: 1223593 (C4 (Web Text))

Max Activating Token Index: 186