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

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

Neuron 1738 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1437. Min Act: -0.0001

Data Index: 106105 (C4 (Web Text))

Max Activating Token Index: 65

Text #1

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1428. Min Act: -0.0001

Data Index: 769973 (C4 (Web Text))

Max Activating Token Index: 388

Text #2

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1377. Min Act: -0.0002

Data Index: 302494 (C4 (Web Text))

Max Activating Token Index: 65

Text #3

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1309. Min Act: -0.0001

Data Index: 43880 (C4 (Web Text))

Max Activating Token Index: 38

Text #4

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1185. Min Act: -0.0001

Data Index: 704003 (C4 (Web Text))

Max Activating Token Index: 788

Text #5

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1228. Min Act: -0.0001

Data Index: 1413850 (Python Code)

Max Activating Token Index: 976

Text #6

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1148. Min Act: -0.0001

Data Index: 362547 (C4 (Web Text))

Max Activating Token Index: 570

Text #7

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1183. Min Act: -0.0001

Data Index: 247741 (C4 (Web Text))

Max Activating Token Index: 549

Text #8

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1061. Min Act: -0.0001

Data Index: 1536932 (Python Code)

Max Activating Token Index: 179

Text #9

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1211. Min Act: -0.0001

Data Index: 888849 (C4 (Web Text))

Max Activating Token Index: 181

Text #10

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1202. Min Act: -0.0001

Data Index: 358676 (C4 (Web Text))

Max Activating Token Index: 29

Text #11

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1044. Min Act: -0.0001

Data Index: 313486 (C4 (Web Text))

Max Activating Token Index: 197

Text #12

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1132. Min Act: -0.0001

Data Index: 1045825 (C4 (Web Text))

Max Activating Token Index: 625

Text #13

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1140. Min Act: -0.0001

Data Index: 1580168 (Python Code)

Max Activating Token Index: 988

Text #14

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1108. Min Act: -0.0001

Data Index: 1398298 (Python Code)

Max Activating Token Index: 1006

Text #15

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1111. Min Act: -0.0001

Data Index: 784567 (C4 (Web Text))

Max Activating Token Index: 221

Text #16

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1102. Min Act: -0.0001

Data Index: 631073 (C4 (Web Text))

Max Activating Token Index: 894

Text #17

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1138. Min Act: -0.0001

Data Index: 1656881 (Python Code)

Max Activating Token Index: 8

Text #18

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1133. Min Act: -0.0001

Data Index: 1291944 (C4 (Web Text))

Max Activating Token Index: 587

Text #19

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1163. Min Act: -0.0001

Data Index: 1153637 (C4 (Web Text))

Max Activating Token Index: 914