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

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

Neuron 1193 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: 0.1341. Min Range: -0.1341

Max Act: 0.1333. Min Act: -0.0003

Data Index: 728990 (C4 (Web Text))

Max Activating Token Index: 198

Text #1

Max Range: 0.1341. Min Range: -0.1341

Max Act: 0.1341. Min Act: -0.0002

Data Index: 1074002 (C4 (Web Text))

Max Activating Token Index: 579

Text #2

Max Range: 0.1341. Min Range: -0.1341

Max Act: 0.1332. Min Act: -0.0003

Data Index: 510546 (C4 (Web Text))

Max Activating Token Index: 734

Text #3

Max Range: 0.1341. Min Range: -0.1341

Max Act: 0.1319. Min Act: -0.0002

Data Index: 1105683 (C4 (Web Text))

Max Activating Token Index: 65

Text #4

Max Range: 0.1341. Min Range: -0.1341

Max Act: 0.1315. Min Act: -0.0003

Data Index: 20010 (C4 (Web Text))

Max Activating Token Index: 130

Text #5

Max Range: 0.1341. Min Range: -0.1341

Max Act: 0.1307. Min Act: -0.0002

Data Index: 1318944 (C4 (Web Text))

Max Activating Token Index: 190

Text #6

Max Range: 0.1341. Min Range: -0.1341

Max Act: 0.1273. Min Act: -0.0002

Data Index: 814350 (C4 (Web Text))

Max Activating Token Index: 223

Text #7

Max Range: 0.1341. Min Range: -0.1341

Max Act: 0.1220. Min Act: -0.0002

Data Index: 1044465 (C4 (Web Text))

Max Activating Token Index: 305

Text #8

Max Range: 0.1341. Min Range: -0.1341

Max Act: 0.1261. Min Act: -0.0002

Data Index: 798091 (C4 (Web Text))

Max Activating Token Index: 150

Text #9

Max Range: 0.1341. Min Range: -0.1341

Max Act: 0.1249. Min Act: -0.0002

Data Index: 651152 (C4 (Web Text))

Max Activating Token Index: 292

Text #10

Max Range: 0.1341. Min Range: -0.1341

Max Act: 0.1210. Min Act: -0.0002

Data Index: 524723 (C4 (Web Text))

Max Activating Token Index: 372

Text #11

Max Range: 0.1341. Min Range: -0.1341

Max Act: 0.1245. Min Act: -0.0002

Data Index: 690585 (C4 (Web Text))

Max Activating Token Index: 226

Text #12

Max Range: 0.1341. Min Range: -0.1341

Max Act: 0.1199. Min Act: -0.0002

Data Index: 110531 (C4 (Web Text))

Max Activating Token Index: 279

Text #13

Max Range: 0.1341. Min Range: -0.1341

Max Act: 0.1180. Min Act: -0.0003

Data Index: 1151227 (C4 (Web Text))

Max Activating Token Index: 552

Text #14

Max Range: 0.1341. Min Range: -0.1341

Max Act: 0.1168. Min Act: -0.0002

Data Index: 143786 (C4 (Web Text))

Max Activating Token Index: 791

Text #15

Max Range: 0.1341. Min Range: -0.1341

Max Act: 0.1158. Min Act: -0.0002

Data Index: 272945 (C4 (Web Text))

Max Activating Token Index: 491

Text #16

Max Range: 0.1341. Min Range: -0.1341

Max Act: 0.1154. Min Act: -0.0002

Data Index: 909133 (C4 (Web Text))

Max Activating Token Index: 98

Text #17

Max Range: 0.1341. Min Range: -0.1341

Max Act: 0.1151. Min Act: -0.0002

Data Index: 1218593 (C4 (Web Text))

Max Activating Token Index: 522

Text #18

Max Range: 0.1341. Min Range: -0.1341

Max Act: 0.1147. Min Act: -0.0002

Data Index: 214809 (C4 (Web Text))

Max Activating Token Index: 404

Text #19

Max Range: 0.1341. Min Range: -0.1341

Max Act: 0.1144. Min Act: -0.0002

Data Index: 847569 (C4 (Web Text))

Max Activating Token Index: 341