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

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

Neuron 1908 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0208. Min Act: -0.0005

Data Index: 1096622 (C4 (Web Text))

Max Activating Token Index: 744

Text #1

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0202. Min Act: -0.0005

Data Index: 351434 (C4 (Web Text))

Max Activating Token Index: 301

Text #2

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0201. Min Act: -0.0005

Data Index: 980549 (C4 (Web Text))

Max Activating Token Index: 808

Text #3

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0196. Min Act: -0.0005

Data Index: 620422 (C4 (Web Text))

Max Activating Token Index: 897

Text #4

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0198. Min Act: -0.0005

Data Index: 1185155 (C4 (Web Text))

Max Activating Token Index: 791

Text #5

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0196. Min Act: -0.0005

Data Index: 631002 (C4 (Web Text))

Max Activating Token Index: 874

Text #6

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0203. Min Act: -0.0005

Data Index: 606670 (C4 (Web Text))

Max Activating Token Index: 677

Text #7

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0189. Min Act: -0.0005

Data Index: 1147082 (C4 (Web Text))

Max Activating Token Index: 634

Text #8

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0193. Min Act: -0.0005

Data Index: 407614 (C4 (Web Text))

Max Activating Token Index: 725

Text #9

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0188. Min Act: -0.0005

Data Index: 1117087 (C4 (Web Text))

Max Activating Token Index: 670

Text #10

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0193. Min Act: -0.0005

Data Index: 156056 (C4 (Web Text))

Max Activating Token Index: 663

Text #11

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0192. Min Act: -0.0005

Data Index: 846949 (C4 (Web Text))

Max Activating Token Index: 718

Text #12

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0183. Min Act: -0.0005

Data Index: 984768 (C4 (Web Text))

Max Activating Token Index: 691

Text #13

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0191. Min Act: -0.0005

Data Index: 1116706 (C4 (Web Text))

Max Activating Token Index: 782

Text #14

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0202. Min Act: -0.0005

Data Index: 719466 (C4 (Web Text))

Max Activating Token Index: 712

Text #15

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0190. Min Act: -0.0005

Data Index: 1013000 (C4 (Web Text))

Max Activating Token Index: 760

Text #16

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0191. Min Act: -0.0005

Data Index: 1117752 (C4 (Web Text))

Max Activating Token Index: 596

Text #17

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0182. Min Act: -0.0005

Data Index: 301427 (C4 (Web Text))

Max Activating Token Index: 431

Text #18

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0187. Min Act: -0.0005

Data Index: 366316 (C4 (Web Text))

Max Activating Token Index: 93

Text #19

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0188. Min Act: -0.0005

Data Index: 597365 (C4 (Web Text))

Max Activating Token Index: 681