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

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

Neuron 4031 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: 0.1872. Min Range: -0.1872

Max Act: 0.1872. Min Act: -0.0000

Data Index: 1314128 (C4 (Web Text))

Max Activating Token Index: 203

Text #1

Max Range: 0.1872. Min Range: -0.1872

Max Act: 0.1448. Min Act: -0.0000

Data Index: 204468 (C4 (Web Text))

Max Activating Token Index: 137

Text #2

Max Range: 0.1872. Min Range: -0.1872

Max Act: 0.1472. Min Act: -0.0000

Data Index: 470182 (C4 (Web Text))

Max Activating Token Index: 428

Text #3

Max Range: 0.1872. Min Range: -0.1872

Max Act: 0.1395. Min Act: -0.0000

Data Index: 468517 (C4 (Web Text))

Max Activating Token Index: 171

Text #4

Max Range: 0.1872. Min Range: -0.1872

Max Act: 0.1359. Min Act: -0.0000

Data Index: 779246 (C4 (Web Text))

Max Activating Token Index: 423

Text #5

Max Range: 0.1872. Min Range: -0.1872

Max Act: 0.1343. Min Act: -0.0000

Data Index: 612175 (C4 (Web Text))

Max Activating Token Index: 293

Text #6

Max Range: 0.1872. Min Range: -0.1872

Max Act: 0.1246. Min Act: -0.0000

Data Index: 1008617 (C4 (Web Text))

Max Activating Token Index: 218

Text #7

Max Range: 0.1872. Min Range: -0.1872

Max Act: 0.1276. Min Act: -0.0000

Data Index: 829089 (C4 (Web Text))

Max Activating Token Index: 460

Text #8

Max Range: 0.1872. Min Range: -0.1872

Max Act: 0.1191. Min Act: -0.0000

Data Index: 633230 (C4 (Web Text))

Max Activating Token Index: 1016

Text #9

Max Range: 0.1872. Min Range: -0.1872

Max Act: 0.1262. Min Act: -0.0000

Data Index: 671127 (C4 (Web Text))

Max Activating Token Index: 113

Text #10

Max Range: 0.1872. Min Range: -0.1872

Max Act: 0.1265. Min Act: -0.0000

Data Index: 958216 (C4 (Web Text))

Max Activating Token Index: 629

Text #11

Max Range: 0.1872. Min Range: -0.1872

Max Act: 0.1212. Min Act: -0.0000

Data Index: 633197 (C4 (Web Text))

Max Activating Token Index: 342

Text #12

Max Range: 0.1872. Min Range: -0.1872

Max Act: 0.1150. Min Act: -0.0000

Data Index: 456343 (C4 (Web Text))

Max Activating Token Index: 789

Text #13

Max Range: 0.1872. Min Range: -0.1872

Max Act: 0.1166. Min Act: -0.0000

Data Index: 560779 (C4 (Web Text))

Max Activating Token Index: 389

Text #14

Max Range: 0.1872. Min Range: -0.1872

Max Act: 0.1251. Min Act: -0.0000

Data Index: 57580 (C4 (Web Text))

Max Activating Token Index: 991

Text #15

Max Range: 0.1872. Min Range: -0.1872

Max Act: 0.1210. Min Act: -0.0000

Data Index: 897716 (C4 (Web Text))

Max Activating Token Index: 783

Text #16

Max Range: 0.1872. Min Range: -0.1872

Max Act: 0.1320. Min Act: -0.0000

Data Index: 1136643 (C4 (Web Text))

Max Activating Token Index: 522

Text #17

Max Range: 0.1872. Min Range: -0.1872

Max Act: 0.1162. Min Act: -0.0000

Data Index: 1126193 (C4 (Web Text))

Max Activating Token Index: 268

Text #18

Max Range: 0.1872. Min Range: -0.1872

Max Act: 0.1147. Min Act: -0.0000

Data Index: 1094288 (C4 (Web Text))

Max Activating Token Index: 38

Text #19

Max Range: 0.1872. Min Range: -0.1872

Max Act: 0.1066. Min Act: -0.0000

Data Index: 311692 (C4 (Web Text))

Max Activating Token Index: 542