Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 705 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0204. Min Range: -0.0204

Max Act: 0.0201. Min Act: -0.0003

Data Index: 1300534 (C4 (Web Text))

Max Activating Token Index: 13

Text #1

Max Range: 0.0204. Min Range: -0.0204

Max Act: 0.0204. Min Act: -0.0003

Data Index: 445372 (C4 (Web Text))

Max Activating Token Index: 141

Text #2

Max Range: 0.0204. Min Range: -0.0204

Max Act: 0.0200. Min Act: -0.0003

Data Index: 1530628 (Python Code)

Max Activating Token Index: 382

Text #3

Max Range: 0.0204. Min Range: -0.0204

Max Act: 0.0191. Min Act: -0.0003

Data Index: 1637975 (Python Code)

Max Activating Token Index: 363

Text #4

Max Range: 0.0204. Min Range: -0.0204

Max Act: 0.0180. Min Act: -0.0003

Data Index: 15075 (C4 (Web Text))

Max Activating Token Index: 234

Text #5

Max Range: 0.0204. Min Range: -0.0204

Max Act: 0.0177. Min Act: -0.0003

Data Index: 509189 (C4 (Web Text))

Max Activating Token Index: 277

Text #6

Max Range: 0.0204. Min Range: -0.0204

Max Act: 0.0179. Min Act: -0.0002

Data Index: 1513827 (Python Code)

Max Activating Token Index: 155

Text #7

Max Range: 0.0204. Min Range: -0.0204

Max Act: 0.0182. Min Act: -0.0003

Data Index: 236594 (C4 (Web Text))

Max Activating Token Index: 82

Text #8

Max Range: 0.0204. Min Range: -0.0204

Max Act: 0.0178. Min Act: -0.0002

Data Index: 1413937 (Python Code)

Max Activating Token Index: 424

Text #9

Max Range: 0.0204. Min Range: -0.0204

Max Act: 0.0174. Min Act: -0.0003

Data Index: 810733 (C4 (Web Text))

Max Activating Token Index: 457

Text #10

Max Range: 0.0204. Min Range: -0.0204

Max Act: 0.0171. Min Act: -0.0003

Data Index: 1613305 (Python Code)

Max Activating Token Index: 567

Text #11

Max Range: 0.0204. Min Range: -0.0204

Max Act: 0.0174. Min Act: -0.0003

Data Index: 950981 (C4 (Web Text))

Max Activating Token Index: 300

Text #12

Max Range: 0.0204. Min Range: -0.0204

Max Act: 0.0170. Min Act: -0.0003

Data Index: 1422324 (Python Code)

Max Activating Token Index: 484

Text #13

Max Range: 0.0204. Min Range: -0.0204

Max Act: 0.0172. Min Act: -0.0003

Data Index: 1291591 (C4 (Web Text))

Max Activating Token Index: 438

Text #14

Max Range: 0.0204. Min Range: -0.0204

Max Act: 0.0172. Min Act: -0.0003

Data Index: 181093 (C4 (Web Text))

Max Activating Token Index: 669

Text #15

Max Range: 0.0204. Min Range: -0.0204

Max Act: 0.0168. Min Act: -0.0003

Data Index: 1622032 (Python Code)

Max Activating Token Index: 528

Text #16

Max Range: 0.0204. Min Range: -0.0204

Max Act: 0.0166. Min Act: -0.0003

Data Index: 499583 (C4 (Web Text))

Max Activating Token Index: 128

Text #17

Max Range: 0.0204. Min Range: -0.0204

Max Act: 0.0171. Min Act: -0.0002

Data Index: 1541739 (Python Code)

Max Activating Token Index: 150

Text #18

Max Range: 0.0204. Min Range: -0.0204

Max Act: 0.0164. Min Act: -0.0003

Data Index: 61184 (C4 (Web Text))

Max Activating Token Index: 1011

Text #19

Max Range: 0.0204. Min Range: -0.0204

Max Act: 0.0171. Min Act: -0.0003

Data Index: 375913 (C4 (Web Text))

Max Activating Token Index: 93