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

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

Neuron 4622 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1500. Min Range: -0.1500

Max Act: 0.1500. Min Act: -0.0000

Data Index: 933559 (C4 (Web Text))

Max Activating Token Index: 161

Text #1

Max Range: 0.1500. Min Range: -0.1500

Max Act: 0.1383. Min Act: -0.0000

Data Index: 1110874 (C4 (Web Text))

Max Activating Token Index: 187

Text #2

Max Range: 0.1500. Min Range: -0.1500

Max Act: 0.1392. Min Act: -0.0000

Data Index: 554310 (C4 (Web Text))

Max Activating Token Index: 254

Text #3

Max Range: 0.1500. Min Range: -0.1500

Max Act: 0.1414. Min Act: -0.0000

Data Index: 751959 (C4 (Web Text))

Max Activating Token Index: 87

Text #4

Max Range: 0.1500. Min Range: -0.1500

Max Act: 0.1248. Min Act: -0.0000

Data Index: 140760 (C4 (Web Text))

Max Activating Token Index: 217

Text #5

Max Range: 0.1500. Min Range: -0.1500

Max Act: 0.1326. Min Act: -0.0000

Data Index: 525594 (C4 (Web Text))

Max Activating Token Index: 179

Text #6

Max Range: 0.1500. Min Range: -0.1500

Max Act: 0.1327. Min Act: -0.0000

Data Index: 174535 (C4 (Web Text))

Max Activating Token Index: 212

Text #7

Max Range: 0.1500. Min Range: -0.1500

Max Act: 0.1315. Min Act: -0.0000

Data Index: 658333 (C4 (Web Text))

Max Activating Token Index: 291

Text #8

Max Range: 0.1500. Min Range: -0.1500

Max Act: 0.1239. Min Act: -0.0000

Data Index: 458721 (C4 (Web Text))

Max Activating Token Index: 195

Text #9

Max Range: 0.1500. Min Range: -0.1500

Max Act: 0.1172. Min Act: -0.0000

Data Index: 597591 (C4 (Web Text))

Max Activating Token Index: 363

Text #10

Max Range: 0.1500. Min Range: -0.1500

Max Act: 0.1290. Min Act: -0.0000

Data Index: 1090188 (C4 (Web Text))

Max Activating Token Index: 912

Text #11

Max Range: 0.1500. Min Range: -0.1500

Max Act: 0.1198. Min Act: -0.0000

Data Index: 1390295 (Python Code)

Max Activating Token Index: 991

Text #12

Max Range: 0.1500. Min Range: -0.1500

Max Act: 0.1171. Min Act: -0.0000

Data Index: 1620964 (Python Code)

Max Activating Token Index: 529

Text #13

Max Range: 0.1500. Min Range: -0.1500

Max Act: 0.1124. Min Act: -0.0000

Data Index: 1555026 (Python Code)

Max Activating Token Index: 717

Text #14

Max Range: 0.1500. Min Range: -0.1500

Max Act: 0.1202. Min Act: -0.0000

Data Index: 70293 (C4 (Web Text))

Max Activating Token Index: 86

Text #15

Max Range: 0.1500. Min Range: -0.1500

Max Act: 0.1161. Min Act: -0.0000

Data Index: 923708 (C4 (Web Text))

Max Activating Token Index: 317

Text #16

Max Range: 0.1500. Min Range: -0.1500

Max Act: 0.1159. Min Act: -0.0000

Data Index: 836037 (C4 (Web Text))

Max Activating Token Index: 901

Text #17

Max Range: 0.1500. Min Range: -0.1500

Max Act: 0.1214. Min Act: -0.0000

Data Index: 711792 (C4 (Web Text))

Max Activating Token Index: 239

Text #18

Max Range: 0.1500. Min Range: -0.1500

Max Act: 0.1157. Min Act: -0.0000

Data Index: 1504046 (Python Code)

Max Activating Token Index: 55

Text #19

Max Range: 0.1500. Min Range: -0.1500

Max Act: 0.1117. Min Act: -0.0000

Data Index: 1197350 (C4 (Web Text))

Max Activating Token Index: 599