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

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

Neuron 1586 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: 0.1375. Min Range: -0.1375

Max Act: 0.1375. Min Act: -0.0001

Data Index: 608488 (C4 (Web Text))

Max Activating Token Index: 197

Text #1

Max Range: 0.1375. Min Range: -0.1375

Max Act: 0.1346. Min Act: -0.0001

Data Index: 587577 (C4 (Web Text))

Max Activating Token Index: 423

Text #2

Max Range: 0.1375. Min Range: -0.1375

Max Act: 0.1263. Min Act: -0.0001

Data Index: 105025 (C4 (Web Text))

Max Activating Token Index: 752

Text #3

Max Range: 0.1375. Min Range: -0.1375

Max Act: 0.1276. Min Act: -0.0001

Data Index: 702769 (C4 (Web Text))

Max Activating Token Index: 240

Text #4

Max Range: 0.1375. Min Range: -0.1375

Max Act: 0.1312. Min Act: -0.0001

Data Index: 374648 (C4 (Web Text))

Max Activating Token Index: 889

Text #5

Max Range: 0.1375. Min Range: -0.1375

Max Act: 0.1178. Min Act: -0.0001

Data Index: 436637 (C4 (Web Text))

Max Activating Token Index: 146

Text #6

Max Range: 0.1375. Min Range: -0.1375

Max Act: 0.1252. Min Act: -0.0001

Data Index: 210565 (C4 (Web Text))

Max Activating Token Index: 727

Text #7

Max Range: 0.1375. Min Range: -0.1375

Max Act: 0.1143. Min Act: -0.0001

Data Index: 548508 (C4 (Web Text))

Max Activating Token Index: 288

Text #8

Max Range: 0.1375. Min Range: -0.1375

Max Act: 0.1142. Min Act: -0.0001

Data Index: 819691 (C4 (Web Text))

Max Activating Token Index: 211

Text #9

Max Range: 0.1375. Min Range: -0.1375

Max Act: 0.1268. Min Act: -0.0001

Data Index: 832612 (C4 (Web Text))

Max Activating Token Index: 20

Text #10

Max Range: 0.1375. Min Range: -0.1375

Max Act: 0.1260. Min Act: -0.0001

Data Index: 1337185 (C4 (Web Text))

Max Activating Token Index: 198

Text #11

Max Range: 0.1375. Min Range: -0.1375

Max Act: 0.1220. Min Act: -0.0001

Data Index: 24030 (C4 (Web Text))

Max Activating Token Index: 208

Text #12

Max Range: 0.1375. Min Range: -0.1375

Max Act: 0.1199. Min Act: -0.0001

Data Index: 80016 (C4 (Web Text))

Max Activating Token Index: 940

Text #13

Max Range: 0.1375. Min Range: -0.1375

Max Act: 0.1217. Min Act: -0.0001

Data Index: 1175814 (C4 (Web Text))

Max Activating Token Index: 263

Text #14

Max Range: 0.1375. Min Range: -0.1375

Max Act: 0.1143. Min Act: -0.0001

Data Index: 802798 (C4 (Web Text))

Max Activating Token Index: 896

Text #15

Max Range: 0.1375. Min Range: -0.1375

Max Act: 0.1187. Min Act: -0.0001

Data Index: 856533 (C4 (Web Text))

Max Activating Token Index: 466

Text #16

Max Range: 0.1375. Min Range: -0.1375

Max Act: 0.1187. Min Act: -0.0001

Data Index: 1358832 (C4 (Web Text))

Max Activating Token Index: 151

Text #17

Max Range: 0.1375. Min Range: -0.1375

Max Act: 0.1126. Min Act: -0.0001

Data Index: 415578 (C4 (Web Text))

Max Activating Token Index: 308

Text #18

Max Range: 0.1375. Min Range: -0.1375

Max Act: 0.1164. Min Act: -0.0001

Data Index: 619196 (C4 (Web Text))

Max Activating Token Index: 303

Text #19

Max Range: 0.1375. Min Range: -0.1375

Max Act: 0.1114. Min Act: -0.0001

Data Index: 1059529 (C4 (Web Text))

Max Activating Token Index: 411