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

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

Neuron 2398 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.7229. Min Range: -0.7229

Max Act: 0.7229. Min Act: -0.0000

Data Index: 1093925 (C4 (Web Text))

Max Activating Token Index: 170

Text #1

Max Range: 0.7229. Min Range: -0.7229

Max Act: 0.7119. Min Act: -0.0000

Data Index: 783139 (C4 (Web Text))

Max Activating Token Index: 13

Text #2

Max Range: 0.7229. Min Range: -0.7229

Max Act: 0.6501. Min Act: -0.0000

Data Index: 752794 (C4 (Web Text))

Max Activating Token Index: 219

Text #3

Max Range: 0.7229. Min Range: -0.7229

Max Act: 0.6301. Min Act: -0.0000

Data Index: 8300 (C4 (Web Text))

Max Activating Token Index: 179

Text #4

Max Range: 0.7229. Min Range: -0.7229

Max Act: 0.6095. Min Act: -0.0000

Data Index: 245318 (C4 (Web Text))

Max Activating Token Index: 97

Text #5

Max Range: 0.7229. Min Range: -0.7229

Max Act: 0.5444. Min Act: -0.0000

Data Index: 1587139 (Python Code)

Max Activating Token Index: 440

Text #6

Max Range: 0.7229. Min Range: -0.7229

Max Act: 0.5604. Min Act: -0.0000

Data Index: 1399984 (Python Code)

Max Activating Token Index: 21

Text #7

Max Range: 0.7229. Min Range: -0.7229

Max Act: 0.5481. Min Act: -0.0000

Data Index: 1123965 (C4 (Web Text))

Max Activating Token Index: 539

Text #8

Max Range: 0.7229. Min Range: -0.7229

Max Act: 0.5226. Min Act: -0.0000

Data Index: 1219330 (C4 (Web Text))

Max Activating Token Index: 12

Text #9

Max Range: 0.7229. Min Range: -0.7229

Max Act: 0.4859. Min Act: -0.0000

Data Index: 154402 (C4 (Web Text))

Max Activating Token Index: 231

Text #10

Max Range: 0.7229. Min Range: -0.7229

Max Act: 0.5135. Min Act: -0.0000

Data Index: 1299875 (C4 (Web Text))

Max Activating Token Index: 360

Text #11

Max Range: 0.7229. Min Range: -0.7229

Max Act: 0.4976. Min Act: -0.0000

Data Index: 849516 (C4 (Web Text))

Max Activating Token Index: 178

Text #12

Max Range: 0.7229. Min Range: -0.7229

Max Act: 0.4993. Min Act: -0.0000

Data Index: 240690 (C4 (Web Text))

Max Activating Token Index: 431

Text #13

Max Range: 0.7229. Min Range: -0.7229

Max Act: 0.4928. Min Act: -0.0000

Data Index: 1457923 (Python Code)

Max Activating Token Index: 20

Text #14

Max Range: 0.7229. Min Range: -0.7229

Max Act: 0.5022. Min Act: -0.0000

Data Index: 42199 (C4 (Web Text))

Max Activating Token Index: 861

Text #15

Max Range: 0.7229. Min Range: -0.7229

Max Act: 0.5216. Min Act: -0.0000

Data Index: 1018449 (C4 (Web Text))

Max Activating Token Index: 305

Text #16

Max Range: 0.7229. Min Range: -0.7229

Max Act: 0.5041. Min Act: -0.0000

Data Index: 280497 (C4 (Web Text))

Max Activating Token Index: 245

Text #17

Max Range: 0.7229. Min Range: -0.7229

Max Act: 0.4866. Min Act: -0.0000

Data Index: 216208 (C4 (Web Text))

Max Activating Token Index: 946

Text #18

Max Range: 0.7229. Min Range: -0.7229

Max Act: 0.5417. Min Act: -0.0000

Data Index: 1357550 (C4 (Web Text))

Max Activating Token Index: 811

Text #19

Max Range: 0.7229. Min Range: -0.7229

Max Act: 0.4337. Min Act: -0.0000

Data Index: 1185981 (C4 (Web Text))

Max Activating Token Index: 302