Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1636 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0198. Min Range: -0.0198

Max Act: 0.0198. Min Act: -0.0006

Data Index: 143850 (C4 (Web Text))

Max Activating Token Index: 580

Text #1

Max Range: 0.0198. Min Range: -0.0198

Max Act: 0.0194. Min Act: -0.0006

Data Index: 677682 (C4 (Web Text))

Max Activating Token Index: 435

Text #2

Max Range: 0.0198. Min Range: -0.0198

Max Act: 0.0195. Min Act: -0.0006

Data Index: 1378003 (Python Code)

Max Activating Token Index: 820

Text #3

Max Range: 0.0198. Min Range: -0.0198

Max Act: 0.0188. Min Act: -0.0006

Data Index: 1107646 (C4 (Web Text))

Max Activating Token Index: 95

Text #4

Max Range: 0.0198. Min Range: -0.0198

Max Act: 0.0188. Min Act: -0.0006

Data Index: 321165 (C4 (Web Text))

Max Activating Token Index: 498

Text #5

Max Range: 0.0198. Min Range: -0.0198

Max Act: 0.0192. Min Act: -0.0006

Data Index: 1394934 (Python Code)

Max Activating Token Index: 850

Text #6

Max Range: 0.0198. Min Range: -0.0198

Max Act: 0.0188. Min Act: -0.0005

Data Index: 1384995 (Python Code)

Max Activating Token Index: 975

Text #7

Max Range: 0.0198. Min Range: -0.0198

Max Act: 0.0186. Min Act: -0.0006

Data Index: 1378085 (Python Code)

Max Activating Token Index: 337

Text #8

Max Range: 0.0198. Min Range: -0.0198

Max Act: 0.0191. Min Act: -0.0006

Data Index: 1640932 (Python Code)

Max Activating Token Index: 266

Text #9

Max Range: 0.0198. Min Range: -0.0198

Max Act: 0.0186. Min Act: -0.0006

Data Index: 280456 (C4 (Web Text))

Max Activating Token Index: 404

Text #10

Max Range: 0.0198. Min Range: -0.0198

Max Act: 0.0186. Min Act: -0.0006

Data Index: 734951 (C4 (Web Text))

Max Activating Token Index: 759

Text #11

Max Range: 0.0198. Min Range: -0.0198

Max Act: 0.0185. Min Act: -0.0006

Data Index: 591223 (C4 (Web Text))

Max Activating Token Index: 489

Text #12

Max Range: 0.0198. Min Range: -0.0198

Max Act: 0.0184. Min Act: -0.0006

Data Index: 570719 (C4 (Web Text))

Max Activating Token Index: 882

Text #13

Max Range: 0.0198. Min Range: -0.0198

Max Act: 0.0184. Min Act: -0.0006

Data Index: 1640326 (Python Code)

Max Activating Token Index: 282

Text #14

Max Range: 0.0198. Min Range: -0.0198

Max Act: 0.0180. Min Act: -0.0006

Data Index: 1161655 (C4 (Web Text))

Max Activating Token Index: 508

Text #15

Max Range: 0.0198. Min Range: -0.0198

Max Act: 0.0179. Min Act: -0.0006

Data Index: 1136573 (C4 (Web Text))

Max Activating Token Index: 552

Text #16

Max Range: 0.0198. Min Range: -0.0198

Max Act: 0.0177. Min Act: -0.0006

Data Index: 1515734 (Python Code)

Max Activating Token Index: 204

Text #17

Max Range: 0.0198. Min Range: -0.0198

Max Act: 0.0182. Min Act: -0.0006

Data Index: 444866 (C4 (Web Text))

Max Activating Token Index: 184

Text #18

Max Range: 0.0198. Min Range: -0.0198

Max Act: 0.0177. Min Act: -0.0006

Data Index: 1202617 (C4 (Web Text))

Max Activating Token Index: 220

Text #19

Max Range: 0.0198. Min Range: -0.0198

Max Act: 0.0179. Min Act: -0.0006

Data Index: 483230 (C4 (Web Text))

Max Activating Token Index: 609