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

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

Neuron 1101 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0271. Min Act: -0.0001

Data Index: 123685 (C4 (Web Text))

Max Activating Token Index: 1016

Text #1

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0228. Min Act: -0.0001

Data Index: 872631 (C4 (Web Text))

Max Activating Token Index: 1021

Text #2

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0227. Min Act: -0.0001

Data Index: 1392157 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0197. Min Act: -0.0001

Data Index: 550764 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0194. Min Act: -0.0001

Data Index: 447154 (C4 (Web Text))

Max Activating Token Index: 1000

Text #5

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0186. Min Act: -0.0001

Data Index: 449925 (C4 (Web Text))

Max Activating Token Index: 1015

Text #6

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0183. Min Act: -0.0001

Data Index: 13002 (C4 (Web Text))

Max Activating Token Index: 1021

Text #7

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0190. Min Act: -0.0001

Data Index: 665815 (C4 (Web Text))

Max Activating Token Index: 980

Text #8

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0185. Min Act: -0.0001

Data Index: 1415299 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0171. Min Act: -0.0001

Data Index: 387805 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0173. Min Act: -0.0001

Data Index: 31241 (C4 (Web Text))

Max Activating Token Index: 1019

Text #11

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0171. Min Act: -0.0001

Data Index: 332051 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0174. Min Act: -0.0001

Data Index: 1041662 (C4 (Web Text))

Max Activating Token Index: 1004

Text #13

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0168. Min Act: -0.0001

Data Index: 1600379 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0163. Min Act: -0.0001

Data Index: 928048 (C4 (Web Text))

Max Activating Token Index: 1019

Text #15

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0164. Min Act: -0.0001

Data Index: 245979 (C4 (Web Text))

Max Activating Token Index: 1016

Text #16

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0165. Min Act: -0.0001

Data Index: 622973 (C4 (Web Text))

Max Activating Token Index: 1022

Text #17

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0163. Min Act: -0.0001

Data Index: 1461032 (Python Code)

Max Activating Token Index: 1023

Text #18

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0171. Min Act: -0.0001

Data Index: 892100 (C4 (Web Text))

Max Activating Token Index: 1017

Text #19

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0153. Min Act: -0.0001

Data Index: 715524 (C4 (Web Text))

Max Activating Token Index: 1015