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

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

Neuron 2587 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: 0.1483. Min Range: -0.1483

Max Act: 0.1483. Min Act: -0.0001

Data Index: 205240 (C4 (Web Text))

Max Activating Token Index: 775

Text #1

Max Range: 0.1483. Min Range: -0.1483

Max Act: 0.1420. Min Act: -0.0001

Data Index: 578937 (C4 (Web Text))

Max Activating Token Index: 380

Text #2

Max Range: 0.1483. Min Range: -0.1483

Max Act: 0.1344. Min Act: -0.0001

Data Index: 297743 (C4 (Web Text))

Max Activating Token Index: 165

Text #3

Max Range: 0.1483. Min Range: -0.1483

Max Act: 0.1408. Min Act: -0.0001

Data Index: 591608 (C4 (Web Text))

Max Activating Token Index: 580

Text #4

Max Range: 0.1483. Min Range: -0.1483

Max Act: 0.1287. Min Act: -0.0001

Data Index: 953775 (C4 (Web Text))

Max Activating Token Index: 321

Text #5

Max Range: 0.1483. Min Range: -0.1483

Max Act: 0.1396. Min Act: -0.0001

Data Index: 715036 (C4 (Web Text))

Max Activating Token Index: 888

Text #6

Max Range: 0.1483. Min Range: -0.1483

Max Act: 0.1311. Min Act: -0.0001

Data Index: 1076750 (C4 (Web Text))

Max Activating Token Index: 1009

Text #7

Max Range: 0.1483. Min Range: -0.1483

Max Act: 0.1302. Min Act: -0.0001

Data Index: 502825 (C4 (Web Text))

Max Activating Token Index: 471

Text #8

Max Range: 0.1483. Min Range: -0.1483

Max Act: 0.1341. Min Act: -0.0001

Data Index: 1279532 (C4 (Web Text))

Max Activating Token Index: 234

Text #9

Max Range: 0.1483. Min Range: -0.1483

Max Act: 0.1216. Min Act: -0.0001

Data Index: 1359509 (C4 (Web Text))

Max Activating Token Index: 195

Text #10

Max Range: 0.1483. Min Range: -0.1483

Max Act: 0.1233. Min Act: -0.0001

Data Index: 1124256 (C4 (Web Text))

Max Activating Token Index: 470

Text #11

Max Range: 0.1483. Min Range: -0.1483

Max Act: 0.1172. Min Act: -0.0001

Data Index: 128241 (C4 (Web Text))

Max Activating Token Index: 566

Text #12

Max Range: 0.1483. Min Range: -0.1483

Max Act: 0.1269. Min Act: -0.0001

Data Index: 67592 (C4 (Web Text))

Max Activating Token Index: 72

Text #13

Max Range: 0.1483. Min Range: -0.1483

Max Act: 0.1164. Min Act: -0.0001

Data Index: 177317 (C4 (Web Text))

Max Activating Token Index: 131

Text #14

Max Range: 0.1483. Min Range: -0.1483

Max Act: 0.1207. Min Act: -0.0001

Data Index: 549000 (C4 (Web Text))

Max Activating Token Index: 139

Text #15

Max Range: 0.1483. Min Range: -0.1483

Max Act: 0.1138. Min Act: -0.0001

Data Index: 273966 (C4 (Web Text))

Max Activating Token Index: 145

Text #16

Max Range: 0.1483. Min Range: -0.1483

Max Act: 0.1135. Min Act: -0.0001

Data Index: 793425 (C4 (Web Text))

Max Activating Token Index: 83

Text #17

Max Range: 0.1483. Min Range: -0.1483

Max Act: 0.1016. Min Act: -0.0001

Data Index: 1109535 (C4 (Web Text))

Max Activating Token Index: 190

Text #18

Max Range: 0.1483. Min Range: -0.1483

Max Act: 0.1185. Min Act: -0.0001

Data Index: 264155 (C4 (Web Text))

Max Activating Token Index: 694

Text #19

Max Range: 0.1483. Min Range: -0.1483

Max Act: 0.1150. Min Act: -0.0001

Data Index: 489655 (C4 (Web Text))

Max Activating Token Index: 598