Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3845 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1550. Min Range: -0.1550

Max Act: 0.1550. Min Act: -0.0000

Data Index: 914329 (C4 (Web Text))

Max Activating Token Index: 282

Text #1

Max Range: 0.1550. Min Range: -0.1550

Max Act: 0.1246. Min Act: -0.0000

Data Index: 733231 (C4 (Web Text))

Max Activating Token Index: 166

Text #2

Max Range: 0.1550. Min Range: -0.1550

Max Act: 0.1274. Min Act: -0.0000

Data Index: 939704 (C4 (Web Text))

Max Activating Token Index: 663

Text #3

Max Range: 0.1550. Min Range: -0.1550

Max Act: 0.1303. Min Act: -0.0000

Data Index: 638841 (C4 (Web Text))

Max Activating Token Index: 175

Text #4

Max Range: 0.1550. Min Range: -0.1550

Max Act: 0.1211. Min Act: -0.0000

Data Index: 1119310 (C4 (Web Text))

Max Activating Token Index: 793

Text #5

Max Range: 0.1550. Min Range: -0.1550

Max Act: 0.1249. Min Act: -0.0000

Data Index: 508477 (C4 (Web Text))

Max Activating Token Index: 839

Text #6

Max Range: 0.1550. Min Range: -0.1550

Max Act: 0.1188. Min Act: -0.0001

Data Index: 445941 (C4 (Web Text))

Max Activating Token Index: 273

Text #7

Max Range: 0.1550. Min Range: -0.1550

Max Act: 0.1278. Min Act: -0.0001

Data Index: 431377 (C4 (Web Text))

Max Activating Token Index: 341

Text #8

Max Range: 0.1550. Min Range: -0.1550

Max Act: 0.1189. Min Act: -0.0000

Data Index: 694333 (C4 (Web Text))

Max Activating Token Index: 523

Text #9

Max Range: 0.1550. Min Range: -0.1550

Max Act: 0.1326. Min Act: -0.0000

Data Index: 914991 (C4 (Web Text))

Max Activating Token Index: 326

Text #10

Max Range: 0.1550. Min Range: -0.1550

Max Act: 0.1232. Min Act: -0.0000

Data Index: 635382 (C4 (Web Text))

Max Activating Token Index: 699

Text #11

Max Range: 0.1550. Min Range: -0.1550

Max Act: 0.1199. Min Act: -0.0000

Data Index: 274990 (C4 (Web Text))

Max Activating Token Index: 463

Text #12

Max Range: 0.1550. Min Range: -0.1550

Max Act: 0.1194. Min Act: -0.0000

Data Index: 1133190 (C4 (Web Text))

Max Activating Token Index: 799

Text #13

Max Range: 0.1550. Min Range: -0.1550

Max Act: 0.1107. Min Act: -0.0000

Data Index: 48874 (C4 (Web Text))

Max Activating Token Index: 172

Text #14

Max Range: 0.1550. Min Range: -0.1550

Max Act: 0.1176. Min Act: -0.0000

Data Index: 467556 (C4 (Web Text))

Max Activating Token Index: 920

Text #15

Max Range: 0.1550. Min Range: -0.1550

Max Act: 0.1156. Min Act: -0.0001

Data Index: 1215938 (C4 (Web Text))

Max Activating Token Index: 1017

Text #16

Max Range: 0.1550. Min Range: -0.1550

Max Act: 0.1233. Min Act: -0.0000

Data Index: 831938 (C4 (Web Text))

Max Activating Token Index: 97

Text #17

Max Range: 0.1550. Min Range: -0.1550

Max Act: 0.1011. Min Act: -0.0000

Data Index: 887854 (C4 (Web Text))

Max Activating Token Index: 559

Text #18

Max Range: 0.1550. Min Range: -0.1550

Max Act: 0.1241. Min Act: -0.0001

Data Index: 1043063 (C4 (Web Text))

Max Activating Token Index: 296

Text #19

Max Range: 0.1550. Min Range: -0.1550

Max Act: 0.1162. Min Act: -0.0000

Data Index: 1218099 (C4 (Web Text))

Max Activating Token Index: 260