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

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

Neuron 4856 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: 0.1399. Min Range: -0.1399

Max Act: 0.1399. Min Act: -0.0002

Data Index: 1025738 (C4 (Web Text))

Max Activating Token Index: 191

Text #1

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.1264. Min Act: -0.0002

Data Index: 841808 (C4 (Web Text))

Max Activating Token Index: 272

Text #2

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.1314. Min Act: -0.0002

Data Index: 33856 (C4 (Web Text))

Max Activating Token Index: 365

Text #3

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.1275. Min Act: -0.0002

Data Index: 125926 (C4 (Web Text))

Max Activating Token Index: 482

Text #4

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.1394. Min Act: -0.0002

Data Index: 611526 (C4 (Web Text))

Max Activating Token Index: 831

Text #5

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.1203. Min Act: -0.0002

Data Index: 854767 (C4 (Web Text))

Max Activating Token Index: 271

Text #6

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.1349. Min Act: -0.0002

Data Index: 672704 (C4 (Web Text))

Max Activating Token Index: 245

Text #7

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.1196. Min Act: -0.0002

Data Index: 920361 (C4 (Web Text))

Max Activating Token Index: 585

Text #8

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.1233. Min Act: -0.0002

Data Index: 1187531 (C4 (Web Text))

Max Activating Token Index: 334

Text #9

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.1357. Min Act: -0.0002

Data Index: 1093729 (C4 (Web Text))

Max Activating Token Index: 243

Text #10

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.1241. Min Act: -0.0002

Data Index: 1051622 (C4 (Web Text))

Max Activating Token Index: 112

Text #11

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.1111. Min Act: -0.0002

Data Index: 928477 (C4 (Web Text))

Max Activating Token Index: 697

Text #12

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.1004. Min Act: -0.0002

Data Index: 746890 (C4 (Web Text))

Max Activating Token Index: 259

Text #13

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.0986. Min Act: -0.0002

Data Index: 158134 (C4 (Web Text))

Max Activating Token Index: 764

Text #14

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.1212. Min Act: -0.0002

Data Index: 812067 (C4 (Web Text))

Max Activating Token Index: 816

Text #15

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.1166. Min Act: -0.0002

Data Index: 317882 (C4 (Web Text))

Max Activating Token Index: 439

Text #16

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.1081. Min Act: -0.0002

Data Index: 1343188 (C4 (Web Text))

Max Activating Token Index: 738

Text #17

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.1295. Min Act: -0.0002

Data Index: 1188115 (C4 (Web Text))

Max Activating Token Index: 283

Text #18

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.1132. Min Act: -0.0002

Data Index: 1077454 (C4 (Web Text))

Max Activating Token Index: 358

Text #19

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.1294. Min Act: -0.0002

Data Index: 757532 (C4 (Web Text))

Max Activating Token Index: 416