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

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

Neuron 1083 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0348. Min Act: -0.0002

Data Index: 703074 (C4 (Web Text))

Max Activating Token Index: 922

Text #1

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0308. Min Act: -0.0002

Data Index: 753995 (C4 (Web Text))

Max Activating Token Index: 614

Text #2

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0247. Min Act: -0.0002

Data Index: 44681 (C4 (Web Text))

Max Activating Token Index: 795

Text #3

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0240. Min Act: -0.0002

Data Index: 1225028 (C4 (Web Text))

Max Activating Token Index: 349

Text #4

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0265. Min Act: -0.0002

Data Index: 669247 (C4 (Web Text))

Max Activating Token Index: 956

Text #5

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0208. Min Act: -0.0002

Data Index: 1196532 (C4 (Web Text))

Max Activating Token Index: 134

Text #6

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0204. Min Act: -0.0002

Data Index: 885355 (C4 (Web Text))

Max Activating Token Index: 315

Text #7

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0215. Min Act: -0.0002

Data Index: 687206 (C4 (Web Text))

Max Activating Token Index: 580

Text #8

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0215. Min Act: -0.0002

Data Index: 1276663 (C4 (Web Text))

Max Activating Token Index: 287

Text #9

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0185. Min Act: -0.0002

Data Index: 349819 (C4 (Web Text))

Max Activating Token Index: 249

Text #10

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0200. Min Act: -0.0002

Data Index: 679974 (C4 (Web Text))

Max Activating Token Index: 83

Text #11

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0194. Min Act: -0.0002

Data Index: 692797 (C4 (Web Text))

Max Activating Token Index: 120

Text #12

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0185. Min Act: -0.0002

Data Index: 777140 (C4 (Web Text))

Max Activating Token Index: 832

Text #13

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0208. Min Act: -0.0002

Data Index: 746317 (C4 (Web Text))

Max Activating Token Index: 357

Text #14

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0180. Min Act: -0.0002

Data Index: 306235 (C4 (Web Text))

Max Activating Token Index: 760

Text #15

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0171. Min Act: -0.0002

Data Index: 32850 (C4 (Web Text))

Max Activating Token Index: 361

Text #16

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0183. Min Act: -0.0002

Data Index: 790188 (C4 (Web Text))

Max Activating Token Index: 317

Text #17

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0178. Min Act: -0.0002

Data Index: 1049450 (C4 (Web Text))

Max Activating Token Index: 514

Text #18

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0182. Min Act: -0.0002

Data Index: 1139514 (C4 (Web Text))

Max Activating Token Index: 951

Text #19

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0185. Min Act: -0.0002

Data Index: 938791 (C4 (Web Text))

Max Activating Token Index: 730