Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5678 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0209. Min Act: -0.0002

Data Index: 64892 (C4 (Web Text))

Max Activating Token Index: 1011

Text #1

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0199. Min Act: -0.0001

Data Index: 1134540 (C4 (Web Text))

Max Activating Token Index: 1022

Text #2

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0194. Min Act: -0.0002

Data Index: 754063 (C4 (Web Text))

Max Activating Token Index: 1022

Text #3

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0187. Min Act: -0.0001

Data Index: 332051 (C4 (Web Text))

Max Activating Token Index: 1022

Text #4

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0191. Min Act: -0.0002

Data Index: 1209600 (C4 (Web Text))

Max Activating Token Index: 1015

Text #5

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0183. Min Act: -0.0002

Data Index: 420076 (C4 (Web Text))

Max Activating Token Index: 1016

Text #6

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0181. Min Act: -0.0002

Data Index: 563383 (C4 (Web Text))

Max Activating Token Index: 971

Text #7

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0175. Min Act: -0.0001

Data Index: 244706 (C4 (Web Text))

Max Activating Token Index: 1018

Text #8

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0176. Min Act: -0.0001

Data Index: 808557 (C4 (Web Text))

Max Activating Token Index: 1017

Text #9

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0177. Min Act: -0.0001

Data Index: 1227959 (C4 (Web Text))

Max Activating Token Index: 1020

Text #10

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0175. Min Act: -0.0001

Data Index: 878588 (C4 (Web Text))

Max Activating Token Index: 995

Text #11

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0175. Min Act: -0.0002

Data Index: 1319231 (C4 (Web Text))

Max Activating Token Index: 1003

Text #12

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0172. Min Act: -0.0002

Data Index: 1525602 (Python Code)

Max Activating Token Index: 1023

Text #13

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0173. Min Act: -0.0002

Data Index: 1446996 (Python Code)

Max Activating Token Index: 1001

Text #14

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0172. Min Act: -0.0002

Data Index: 30270 (C4 (Web Text))

Max Activating Token Index: 1014

Text #15

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0171. Min Act: -0.0002

Data Index: 1477434 (Python Code)

Max Activating Token Index: 1019

Text #16

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0168. Min Act: -0.0003

Data Index: 1354480 (C4 (Web Text))

Max Activating Token Index: 1008

Text #17

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0165. Min Act: -0.0002

Data Index: 673584 (C4 (Web Text))

Max Activating Token Index: 1018

Text #18

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0161. Min Act: -0.0002

Data Index: 217149 (C4 (Web Text))

Max Activating Token Index: 1009

Text #19

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0164. Min Act: -0.0002

Data Index: 879996 (C4 (Web Text))

Max Activating Token Index: 1020