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

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

Neuron 1033 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1585. Min Act: -0.0001

Data Index: 1185419 (C4 (Web Text))

Max Activating Token Index: 223

Text #1

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1597. Min Act: -0.0001

Data Index: 705144 (C4 (Web Text))

Max Activating Token Index: 152

Text #2

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1501. Min Act: -0.0001

Data Index: 903729 (C4 (Web Text))

Max Activating Token Index: 1014

Text #3

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1296. Min Act: -0.0001

Data Index: 134888 (C4 (Web Text))

Max Activating Token Index: 634

Text #4

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1281. Min Act: -0.0001

Data Index: 608471 (C4 (Web Text))

Max Activating Token Index: 842

Text #5

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1321. Min Act: -0.0001

Data Index: 1053473 (C4 (Web Text))

Max Activating Token Index: 493

Text #6

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1302. Min Act: -0.0001

Data Index: 908604 (C4 (Web Text))

Max Activating Token Index: 144

Text #7

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1329. Min Act: -0.0001

Data Index: 1305308 (C4 (Web Text))

Max Activating Token Index: 123

Text #8

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1179. Min Act: -0.0001

Data Index: 14757 (C4 (Web Text))

Max Activating Token Index: 768

Text #9

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1280. Min Act: -0.0001

Data Index: 835528 (C4 (Web Text))

Max Activating Token Index: 292

Text #10

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1271. Min Act: -0.0001

Data Index: 1217733 (C4 (Web Text))

Max Activating Token Index: 975

Text #11

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1191. Min Act: -0.0001

Data Index: 180486 (C4 (Web Text))

Max Activating Token Index: 1016

Text #12

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1252. Min Act: -0.0001

Data Index: 903628 (C4 (Web Text))

Max Activating Token Index: 716

Text #13

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1277. Min Act: -0.0001

Data Index: 490792 (C4 (Web Text))

Max Activating Token Index: 613

Text #14

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1271. Min Act: -0.0001

Data Index: 1003781 (C4 (Web Text))

Max Activating Token Index: 332

Text #15

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1189. Min Act: -0.0001

Data Index: 1172612 (C4 (Web Text))

Max Activating Token Index: 784

Text #16

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1215. Min Act: -0.0001

Data Index: 182469 (C4 (Web Text))

Max Activating Token Index: 341

Text #17

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1129. Min Act: -0.0001

Data Index: 335340 (C4 (Web Text))

Max Activating Token Index: 754

Text #18

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1213. Min Act: -0.0001

Data Index: 602721 (C4 (Web Text))

Max Activating Token Index: 190

Text #19

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1128. Min Act: -0.0001

Data Index: 564836 (C4 (Web Text))

Max Activating Token Index: 620