Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 476 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1330. Min Act: -0.0001

Data Index: 235499 (C4 (Web Text))

Max Activating Token Index: 702

Text #1

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1124. Min Act: -0.0001

Data Index: 1278147 (C4 (Web Text))

Max Activating Token Index: 601

Text #2

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1250. Min Act: -0.0001

Data Index: 729258 (C4 (Web Text))

Max Activating Token Index: 34

Text #3

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1217. Min Act: -0.0001

Data Index: 676710 (C4 (Web Text))

Max Activating Token Index: 71

Text #4

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1210. Min Act: -0.0001

Data Index: 348764 (C4 (Web Text))

Max Activating Token Index: 193

Text #5

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1246. Min Act: -0.0001

Data Index: 1187040 (C4 (Web Text))

Max Activating Token Index: 487

Text #6

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1240. Min Act: -0.0001

Data Index: 60175 (C4 (Web Text))

Max Activating Token Index: 259

Text #7

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1160. Min Act: -0.0001

Data Index: 1342373 (C4 (Web Text))

Max Activating Token Index: 115

Text #8

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1194. Min Act: -0.0001

Data Index: 791072 (C4 (Web Text))

Max Activating Token Index: 882

Text #9

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1132. Min Act: -0.0001

Data Index: 1262816 (C4 (Web Text))

Max Activating Token Index: 381

Text #10

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1130. Min Act: -0.0001

Data Index: 816028 (C4 (Web Text))

Max Activating Token Index: 790

Text #11

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1219. Min Act: -0.0001

Data Index: 563173 (C4 (Web Text))

Max Activating Token Index: 239

Text #12

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1205. Min Act: -0.0001

Data Index: 122465 (C4 (Web Text))

Max Activating Token Index: 398

Text #13

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1225. Min Act: -0.0001

Data Index: 729967 (C4 (Web Text))

Max Activating Token Index: 277

Text #14

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1234. Min Act: -0.0001

Data Index: 110212 (C4 (Web Text))

Max Activating Token Index: 285

Text #15

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1154. Min Act: -0.0001

Data Index: 130416 (C4 (Web Text))

Max Activating Token Index: 180

Text #16

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1037. Min Act: -0.0001

Data Index: 778940 (C4 (Web Text))

Max Activating Token Index: 350

Text #17

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1196. Min Act: -0.0001

Data Index: 1237876 (C4 (Web Text))

Max Activating Token Index: 275

Text #18

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1262. Min Act: -0.0001

Data Index: 1060463 (C4 (Web Text))

Max Activating Token Index: 786

Text #19

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1108. Min Act: -0.0001

Data Index: 1150789 (C4 (Web Text))

Max Activating Token Index: 683