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

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

Neuron 1282 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1349. Min Range: -0.1349

Max Act: 0.1349. Min Act: -0.0000

Data Index: 21314 (C4 (Web Text))

Max Activating Token Index: 417

Text #1

Max Range: 0.1349. Min Range: -0.1349

Max Act: 0.1179. Min Act: -0.0000

Data Index: 1262350 (C4 (Web Text))

Max Activating Token Index: 863

Text #2

Max Range: 0.1349. Min Range: -0.1349

Max Act: 0.1229. Min Act: -0.0000

Data Index: 777379 (C4 (Web Text))

Max Activating Token Index: 340

Text #3

Max Range: 0.1349. Min Range: -0.1349

Max Act: 0.1239. Min Act: -0.0000

Data Index: 356248 (C4 (Web Text))

Max Activating Token Index: 367

Text #4

Max Range: 0.1349. Min Range: -0.1349

Max Act: 0.1225. Min Act: -0.0000

Data Index: 39971 (C4 (Web Text))

Max Activating Token Index: 414

Text #5

Max Range: 0.1349. Min Range: -0.1349

Max Act: 0.1221. Min Act: -0.0000

Data Index: 1463241 (Python Code)

Max Activating Token Index: 315

Text #6

Max Range: 0.1349. Min Range: -0.1349

Max Act: 0.1207. Min Act: -0.0000

Data Index: 68314 (C4 (Web Text))

Max Activating Token Index: 613

Text #7

Max Range: 0.1349. Min Range: -0.1349

Max Act: 0.1288. Min Act: -0.0000

Data Index: 1206954 (C4 (Web Text))

Max Activating Token Index: 419

Text #8

Max Range: 0.1349. Min Range: -0.1349

Max Act: 0.1236. Min Act: -0.0000

Data Index: 1423951 (Python Code)

Max Activating Token Index: 554

Text #9

Max Range: 0.1349. Min Range: -0.1349

Max Act: 0.1173. Min Act: -0.0000

Data Index: 586956 (C4 (Web Text))

Max Activating Token Index: 420

Text #10

Max Range: 0.1349. Min Range: -0.1349

Max Act: 0.1155. Min Act: -0.0000

Data Index: 1102663 (C4 (Web Text))

Max Activating Token Index: 398

Text #11

Max Range: 0.1349. Min Range: -0.1349

Max Act: 0.1126. Min Act: -0.0000

Data Index: 1044460 (C4 (Web Text))

Max Activating Token Index: 639

Text #12

Max Range: 0.1349. Min Range: -0.1349

Max Act: 0.1095. Min Act: -0.0000

Data Index: 1456323 (Python Code)

Max Activating Token Index: 703

Text #13

Max Range: 0.1349. Min Range: -0.1349

Max Act: 0.1180. Min Act: -0.0000

Data Index: 471178 (C4 (Web Text))

Max Activating Token Index: 1022

Text #14

Max Range: 0.1349. Min Range: -0.1349

Max Act: 0.1220. Min Act: -0.0000

Data Index: 53997 (C4 (Web Text))

Max Activating Token Index: 175

Text #15

Max Range: 0.1349. Min Range: -0.1349

Max Act: 0.1090. Min Act: -0.0000

Data Index: 553208 (C4 (Web Text))

Max Activating Token Index: 673

Text #16

Max Range: 0.1349. Min Range: -0.1349

Max Act: 0.1153. Min Act: -0.0000

Data Index: 719496 (C4 (Web Text))

Max Activating Token Index: 576

Text #17

Max Range: 0.1349. Min Range: -0.1349

Max Act: 0.0942. Min Act: -0.0000

Data Index: 496525 (C4 (Web Text))

Max Activating Token Index: 830

Text #18

Max Range: 0.1349. Min Range: -0.1349

Max Act: 0.1285. Min Act: -0.0000

Data Index: 952815 (C4 (Web Text))

Max Activating Token Index: 694

Text #19

Max Range: 0.1349. Min Range: -0.1349

Max Act: 0.1201. Min Act: -0.0000

Data Index: 1487511 (Python Code)

Max Activating Token Index: 697