Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1940 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0209. Min Act: -0.0004

Data Index: 505529 (C4 (Web Text))

Max Activating Token Index: 267

Text #1

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0203. Min Act: -0.0004

Data Index: 48559 (C4 (Web Text))

Max Activating Token Index: 715

Text #2

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0201. Min Act: -0.0005

Data Index: 1368246 (Python Code)

Max Activating Token Index: 63

Text #3

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0195. Min Act: -0.0005

Data Index: 1057794 (C4 (Web Text))

Max Activating Token Index: 628

Text #4

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0200. Min Act: -0.0005

Data Index: 1570515 (Python Code)

Max Activating Token Index: 364

Text #5

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0190. Min Act: -0.0005

Data Index: 1630474 (Python Code)

Max Activating Token Index: 977

Text #6

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0195. Min Act: -0.0005

Data Index: 1374280 (Python Code)

Max Activating Token Index: 615

Text #7

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0193. Min Act: -0.0005

Data Index: 1405396 (Python Code)

Max Activating Token Index: 57

Text #8

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0192. Min Act: -0.0005

Data Index: 931439 (C4 (Web Text))

Max Activating Token Index: 116

Text #9

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0191. Min Act: -0.0006

Data Index: 867973 (C4 (Web Text))

Max Activating Token Index: 525

Text #10

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0191. Min Act: -0.0005

Data Index: 1514590 (Python Code)

Max Activating Token Index: 129

Text #11

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0189. Min Act: -0.0005

Data Index: 664256 (C4 (Web Text))

Max Activating Token Index: 211

Text #12

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0189. Min Act: -0.0005

Data Index: 1509714 (Python Code)

Max Activating Token Index: 641

Text #13

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0184. Min Act: -0.0005

Data Index: 999421 (C4 (Web Text))

Max Activating Token Index: 909

Text #14

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0188. Min Act: -0.0005

Data Index: 1519730 (Python Code)

Max Activating Token Index: 57

Text #15

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0188. Min Act: -0.0005

Data Index: 148793 (C4 (Web Text))

Max Activating Token Index: 475

Text #16

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0187. Min Act: -0.0005

Data Index: 84855 (C4 (Web Text))

Max Activating Token Index: 358

Text #17

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0183. Min Act: -0.0005

Data Index: 1074142 (C4 (Web Text))

Max Activating Token Index: 149

Text #18

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0186. Min Act: -0.0005

Data Index: 1375084 (Python Code)

Max Activating Token Index: 50

Text #19

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0182. Min Act: -0.0005

Data Index: 1301506 (C4 (Web Text))

Max Activating Token Index: 878