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

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

Neuron 4306 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: 2.9156. Min Range: -2.9156

Max Act: 2.8332. Min Act: -0.0000

Data Index: 366740 (C4 (Web Text))

Max Activating Token Index: 997

Text #1

Max Range: 2.9156. Min Range: -2.9156

Max Act: 2.7880. Min Act: -0.0000

Data Index: 324798 (C4 (Web Text))

Max Activating Token Index: 983

Text #2

Max Range: 2.9156. Min Range: -2.9156

Max Act: 2.9156. Min Act: -0.0000

Data Index: 1309986 (C4 (Web Text))

Max Activating Token Index: 730

Text #3

Max Range: 2.9156. Min Range: -2.9156

Max Act: 2.7236. Min Act: -0.0000

Data Index: 536803 (C4 (Web Text))

Max Activating Token Index: 651

Text #4

Max Range: 2.9156. Min Range: -2.9156

Max Act: 2.8407. Min Act: -0.0000

Data Index: 1198104 (C4 (Web Text))

Max Activating Token Index: 417

Text #5

Max Range: 2.9156. Min Range: -2.9156

Max Act: 2.6265. Min Act: -0.0000

Data Index: 1203585 (C4 (Web Text))

Max Activating Token Index: 767

Text #6

Max Range: 2.9156. Min Range: -2.9156

Max Act: 2.4374. Min Act: -0.0000

Data Index: 1341663 (C4 (Web Text))

Max Activating Token Index: 58

Text #7

Max Range: 2.9156. Min Range: -2.9156

Max Act: 2.5565. Min Act: -0.0000

Data Index: 651500 (C4 (Web Text))

Max Activating Token Index: 236

Text #8

Max Range: 2.9156. Min Range: -2.9156

Max Act: 2.5316. Min Act: -0.0000

Data Index: 897486 (C4 (Web Text))

Max Activating Token Index: 440

Text #9

Max Range: 2.9156. Min Range: -2.9156

Max Act: 2.5313. Min Act: -0.0000

Data Index: 1280596 (C4 (Web Text))

Max Activating Token Index: 870

Text #10

Max Range: 2.9156. Min Range: -2.9156

Max Act: 2.6089. Min Act: -0.0000

Data Index: 1168364 (C4 (Web Text))

Max Activating Token Index: 86

Text #11

Max Range: 2.9156. Min Range: -2.9156

Max Act: 2.5789. Min Act: -0.0000

Data Index: 304010 (C4 (Web Text))

Max Activating Token Index: 244

Text #12

Max Range: 2.9156. Min Range: -2.9156

Max Act: 2.4370. Min Act: -0.0000

Data Index: 1597387 (Python Code)

Max Activating Token Index: 752

Text #13

Max Range: 2.9156. Min Range: -2.9156

Max Act: 2.4244. Min Act: -0.0000

Data Index: 734912 (C4 (Web Text))

Max Activating Token Index: 691

Text #14

Max Range: 2.9156. Min Range: -2.9156

Max Act: 2.2589. Min Act: -0.0000

Data Index: 1404558 (Python Code)

Max Activating Token Index: 754

Text #15

Max Range: 2.9156. Min Range: -2.9156

Max Act: 2.3445. Min Act: -0.0000

Data Index: 789536 (C4 (Web Text))

Max Activating Token Index: 980

Text #16

Max Range: 2.9156. Min Range: -2.9156

Max Act: 2.4615. Min Act: -0.0000

Data Index: 872283 (C4 (Web Text))

Max Activating Token Index: 1002

Text #17

Max Range: 2.9156. Min Range: -2.9156

Max Act: 2.4500. Min Act: -0.0000

Data Index: 1116368 (C4 (Web Text))

Max Activating Token Index: 1003

Text #18

Max Range: 2.9156. Min Range: -2.9156

Max Act: 2.3061. Min Act: -0.0000

Data Index: 415364 (C4 (Web Text))

Max Activating Token Index: 69

Text #19

Max Range: 2.9156. Min Range: -2.9156

Max Act: 2.2990. Min Act: -0.0000

Data Index: 208594 (C4 (Web Text))

Max Activating Token Index: 24