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

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

Neuron 406 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1315. Min Range: -0.1315

Max Act: 0.1315. Min Act: -0.0001

Data Index: 952056 (C4 (Web Text))

Max Activating Token Index: 707

Text #1

Max Range: 0.1315. Min Range: -0.1315

Max Act: 0.1298. Min Act: -0.0001

Data Index: 410328 (C4 (Web Text))

Max Activating Token Index: 5

Text #2

Max Range: 0.1315. Min Range: -0.1315

Max Act: 0.1253. Min Act: -0.0001

Data Index: 69063 (C4 (Web Text))

Max Activating Token Index: 2

Text #3

Max Range: 0.1315. Min Range: -0.1315

Max Act: 0.1258. Min Act: -0.0001

Data Index: 764629 (C4 (Web Text))

Max Activating Token Index: 320

Text #4

Max Range: 0.1315. Min Range: -0.1315

Max Act: 0.1255. Min Act: -0.0001

Data Index: 1034467 (C4 (Web Text))

Max Activating Token Index: 131

Text #5

Max Range: 0.1315. Min Range: -0.1315

Max Act: 0.1091. Min Act: -0.0001

Data Index: 1120393 (C4 (Web Text))

Max Activating Token Index: 974

Text #6

Max Range: 0.1315. Min Range: -0.1315

Max Act: 0.1230. Min Act: -0.0001

Data Index: 1025376 (C4 (Web Text))

Max Activating Token Index: 995

Text #7

Max Range: 0.1315. Min Range: -0.1315

Max Act: 0.1191. Min Act: -0.0001

Data Index: 63888 (C4 (Web Text))

Max Activating Token Index: 4

Text #8

Max Range: 0.1315. Min Range: -0.1315

Max Act: 0.1180. Min Act: -0.0001

Data Index: 1105269 (C4 (Web Text))

Max Activating Token Index: 448

Text #9

Max Range: 0.1315. Min Range: -0.1315

Max Act: 0.1141. Min Act: -0.0001

Data Index: 1299548 (C4 (Web Text))

Max Activating Token Index: 223

Text #10

Max Range: 0.1315. Min Range: -0.1315

Max Act: 0.1127. Min Act: -0.0001

Data Index: 1241833 (C4 (Web Text))

Max Activating Token Index: 163

Text #11

Max Range: 0.1315. Min Range: -0.1315

Max Act: 0.1145. Min Act: -0.0001

Data Index: 82628 (C4 (Web Text))

Max Activating Token Index: 613

Text #12

Max Range: 0.1315. Min Range: -0.1315

Max Act: 0.1134. Min Act: -0.0001

Data Index: 77829 (C4 (Web Text))

Max Activating Token Index: 867

Text #13

Max Range: 0.1315. Min Range: -0.1315

Max Act: 0.1041. Min Act: -0.0001

Data Index: 1080989 (C4 (Web Text))

Max Activating Token Index: 338

Text #14

Max Range: 0.1315. Min Range: -0.1315

Max Act: 0.1099. Min Act: -0.0001

Data Index: 153805 (C4 (Web Text))

Max Activating Token Index: 488

Text #15

Max Range: 0.1315. Min Range: -0.1315

Max Act: 0.1174. Min Act: -0.0001

Data Index: 1070438 (C4 (Web Text))

Max Activating Token Index: 648

Text #16

Max Range: 0.1315. Min Range: -0.1315

Max Act: 0.1078. Min Act: -0.0001

Data Index: 841347 (C4 (Web Text))

Max Activating Token Index: 379

Text #17

Max Range: 0.1315. Min Range: -0.1315

Max Act: 0.1115. Min Act: -0.0001

Data Index: 1058841 (C4 (Web Text))

Max Activating Token Index: 415

Text #18

Max Range: 0.1315. Min Range: -0.1315

Max Act: 0.1105. Min Act: -0.0001

Data Index: 257723 (C4 (Web Text))

Max Activating Token Index: 97

Text #19

Max Range: 0.1315. Min Range: -0.1315

Max Act: 0.1095. Min Act: -0.0001

Data Index: 1073342 (C4 (Web Text))

Max Activating Token Index: 586