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

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

Neuron 3412 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7294. Min Range: -0.7294

Max Act: 0.7294. Min Act: -0.0001

Data Index: 71445 (C4 (Web Text))

Max Activating Token Index: 612

Text #1

Max Range: 0.7294. Min Range: -0.7294

Max Act: 0.6372. Min Act: -0.0001

Data Index: 183818 (C4 (Web Text))

Max Activating Token Index: 472

Text #2

Max Range: 0.7294. Min Range: -0.7294

Max Act: 0.5976. Min Act: -0.0001

Data Index: 766133 (C4 (Web Text))

Max Activating Token Index: 253

Text #3

Max Range: 0.7294. Min Range: -0.7294

Max Act: 0.6187. Min Act: -0.0001

Data Index: 839225 (C4 (Web Text))

Max Activating Token Index: 36

Text #4

Max Range: 0.7294. Min Range: -0.7294

Max Act: 0.5662. Min Act: -0.0001

Data Index: 1282601 (C4 (Web Text))

Max Activating Token Index: 173

Text #5

Max Range: 0.7294. Min Range: -0.7294

Max Act: 0.5532. Min Act: -0.0001

Data Index: 1339639 (C4 (Web Text))

Max Activating Token Index: 612

Text #6

Max Range: 0.7294. Min Range: -0.7294

Max Act: 0.5595. Min Act: -0.0001

Data Index: 658003 (C4 (Web Text))

Max Activating Token Index: 39

Text #7

Max Range: 0.7294. Min Range: -0.7294

Max Act: 0.5330. Min Act: -0.0001

Data Index: 124208 (C4 (Web Text))

Max Activating Token Index: 262

Text #8

Max Range: 0.7294. Min Range: -0.7294

Max Act: 0.5135. Min Act: -0.0001

Data Index: 174659 (C4 (Web Text))

Max Activating Token Index: 92

Text #9

Max Range: 0.7294. Min Range: -0.7294

Max Act: 0.5379. Min Act: -0.0001

Data Index: 1267185 (C4 (Web Text))

Max Activating Token Index: 490

Text #10

Max Range: 0.7294. Min Range: -0.7294

Max Act: 0.5409. Min Act: -0.0001

Data Index: 50375 (C4 (Web Text))

Max Activating Token Index: 213

Text #11

Max Range: 0.7294. Min Range: -0.7294

Max Act: 0.5104. Min Act: -0.0001

Data Index: 130276 (C4 (Web Text))

Max Activating Token Index: 587

Text #12

Max Range: 0.7294. Min Range: -0.7294

Max Act: 0.4961. Min Act: -0.0001

Data Index: 337906 (C4 (Web Text))

Max Activating Token Index: 23

Text #13

Max Range: 0.7294. Min Range: -0.7294

Max Act: 0.5207. Min Act: -0.0001

Data Index: 47273 (C4 (Web Text))

Max Activating Token Index: 251

Text #14

Max Range: 0.7294. Min Range: -0.7294

Max Act: 0.5033. Min Act: -0.0001

Data Index: 275575 (C4 (Web Text))

Max Activating Token Index: 447

Text #15

Max Range: 0.7294. Min Range: -0.7294

Max Act: 0.5161. Min Act: -0.0001

Data Index: 915744 (C4 (Web Text))

Max Activating Token Index: 482

Text #16

Max Range: 0.7294. Min Range: -0.7294

Max Act: 0.4957. Min Act: -0.0001

Data Index: 663896 (C4 (Web Text))

Max Activating Token Index: 59

Text #17

Max Range: 0.7294. Min Range: -0.7294

Max Act: 0.4829. Min Act: -0.0001

Data Index: 7310 (C4 (Web Text))

Max Activating Token Index: 1011

Text #18

Max Range: 0.7294. Min Range: -0.7294

Max Act: 0.4685. Min Act: -0.0001

Data Index: 165134 (C4 (Web Text))

Max Activating Token Index: 35

Text #19

Max Range: 0.7294. Min Range: -0.7294

Max Act: 0.4992. Min Act: -0.0001

Data Index: 85140 (C4 (Web Text))

Max Activating Token Index: 349