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

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

Neuron 3395 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: 4.5268. Min Range: -4.5268

Max Act: 4.5268. Min Act: -0.0000

Data Index: 817432 (C4 (Web Text))

Max Activating Token Index: 529

Text #1

Max Range: 4.5268. Min Range: -4.5268

Max Act: 4.2172. Min Act: -0.0000

Data Index: 1066836 (C4 (Web Text))

Max Activating Token Index: 123

Text #2

Max Range: 4.5268. Min Range: -4.5268

Max Act: 3.9691. Min Act: -0.0000

Data Index: 1070989 (C4 (Web Text))

Max Activating Token Index: 591

Text #3

Max Range: 4.5268. Min Range: -4.5268

Max Act: 3.7173. Min Act: -0.0000

Data Index: 712050 (C4 (Web Text))

Max Activating Token Index: 184

Text #4

Max Range: 4.5268. Min Range: -4.5268

Max Act: 3.7230. Min Act: -0.0000

Data Index: 903903 (C4 (Web Text))

Max Activating Token Index: 221

Text #5

Max Range: 4.5268. Min Range: -4.5268

Max Act: 3.5446. Min Act: -0.0000

Data Index: 67926 (C4 (Web Text))

Max Activating Token Index: 668

Text #6

Max Range: 4.5268. Min Range: -4.5268

Max Act: 3.5352. Min Act: -0.0000

Data Index: 351168 (C4 (Web Text))

Max Activating Token Index: 60

Text #7

Max Range: 4.5268. Min Range: -4.5268

Max Act: 3.5424. Min Act: -0.0000

Data Index: 343305 (C4 (Web Text))

Max Activating Token Index: 89

Text #8

Max Range: 4.5268. Min Range: -4.5268

Max Act: 3.5144. Min Act: -0.0000

Data Index: 444195 (C4 (Web Text))

Max Activating Token Index: 697

Text #9

Max Range: 4.5268. Min Range: -4.5268

Max Act: 3.5188. Min Act: -0.0000

Data Index: 1086019 (C4 (Web Text))

Max Activating Token Index: 838

Text #10

Max Range: 4.5268. Min Range: -4.5268

Max Act: 3.6399. Min Act: -0.0000

Data Index: 537786 (C4 (Web Text))

Max Activating Token Index: 676

Text #11

Max Range: 4.5268. Min Range: -4.5268

Max Act: 3.3271. Min Act: -0.0000

Data Index: 872563 (C4 (Web Text))

Max Activating Token Index: 900

Text #12

Max Range: 4.5268. Min Range: -4.5268

Max Act: 3.4473. Min Act: -0.0000

Data Index: 156165 (C4 (Web Text))

Max Activating Token Index: 350

Text #13

Max Range: 4.5268. Min Range: -4.5268

Max Act: 3.4145. Min Act: -0.0000

Data Index: 1202632 (C4 (Web Text))

Max Activating Token Index: 140

Text #14

Max Range: 4.5268. Min Range: -4.5268

Max Act: 3.5553. Min Act: -0.0000

Data Index: 814531 (C4 (Web Text))

Max Activating Token Index: 186

Text #15

Max Range: 4.5268. Min Range: -4.5268

Max Act: 3.1974. Min Act: -0.0000

Data Index: 1290135 (C4 (Web Text))

Max Activating Token Index: 324

Text #16

Max Range: 4.5268. Min Range: -4.5268

Max Act: 3.3416. Min Act: -0.0000

Data Index: 374480 (C4 (Web Text))

Max Activating Token Index: 443

Text #17

Max Range: 4.5268. Min Range: -4.5268

Max Act: 3.1800. Min Act: -0.0000

Data Index: 113738 (C4 (Web Text))

Max Activating Token Index: 57

Text #18

Max Range: 4.5268. Min Range: -4.5268

Max Act: 3.5158. Min Act: -0.0000

Data Index: 521333 (C4 (Web Text))

Max Activating Token Index: 908

Text #19

Max Range: 4.5268. Min Range: -4.5268

Max Act: 3.3176. Min Act: -0.0000

Data Index: 926051 (C4 (Web Text))

Max Activating Token Index: 260