Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4677 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1543. Min Range: -0.1543

Max Act: 0.1491. Min Act: -0.0000

Data Index: 946878 (C4 (Web Text))

Max Activating Token Index: 316

Text #1

Max Range: 0.1543. Min Range: -0.1543

Max Act: 0.1543. Min Act: -0.0000

Data Index: 409182 (C4 (Web Text))

Max Activating Token Index: 765

Text #2

Max Range: 0.1543. Min Range: -0.1543

Max Act: 0.1310. Min Act: -0.0000

Data Index: 326667 (C4 (Web Text))

Max Activating Token Index: 307

Text #3

Max Range: 0.1543. Min Range: -0.1543

Max Act: 0.1344. Min Act: -0.0001

Data Index: 753846 (C4 (Web Text))

Max Activating Token Index: 610

Text #4

Max Range: 0.1543. Min Range: -0.1543

Max Act: 0.1371. Min Act: -0.0001

Data Index: 199705 (C4 (Web Text))

Max Activating Token Index: 371

Text #5

Max Range: 0.1543. Min Range: -0.1543

Max Act: 0.1251. Min Act: -0.0001

Data Index: 591300 (C4 (Web Text))

Max Activating Token Index: 716

Text #6

Max Range: 0.1543. Min Range: -0.1543

Max Act: 0.1241. Min Act: -0.0001

Data Index: 727715 (C4 (Web Text))

Max Activating Token Index: 782

Text #7

Max Range: 0.1543. Min Range: -0.1543

Max Act: 0.1224. Min Act: -0.0001

Data Index: 377630 (C4 (Web Text))

Max Activating Token Index: 982

Text #8

Max Range: 0.1543. Min Range: -0.1543

Max Act: 0.1193. Min Act: -0.0000

Data Index: 1356815 (C4 (Web Text))

Max Activating Token Index: 156

Text #9

Max Range: 0.1543. Min Range: -0.1543

Max Act: 0.1141. Min Act: -0.0001

Data Index: 975380 (C4 (Web Text))

Max Activating Token Index: 928

Text #10

Max Range: 0.1543. Min Range: -0.1543

Max Act: 0.1220. Min Act: -0.0001

Data Index: 1335852 (C4 (Web Text))

Max Activating Token Index: 548

Text #11

Max Range: 0.1543. Min Range: -0.1543

Max Act: 0.1167. Min Act: -0.0001

Data Index: 1191450 (C4 (Web Text))

Max Activating Token Index: 307

Text #12

Max Range: 0.1543. Min Range: -0.1543

Max Act: 0.1108. Min Act: -0.0001

Data Index: 33540 (C4 (Web Text))

Max Activating Token Index: 312

Text #13

Max Range: 0.1543. Min Range: -0.1543

Max Act: 0.1069. Min Act: -0.0000

Data Index: 656666 (C4 (Web Text))

Max Activating Token Index: 656

Text #14

Max Range: 0.1543. Min Range: -0.1543

Max Act: 0.1109. Min Act: -0.0001

Data Index: 490559 (C4 (Web Text))

Max Activating Token Index: 349

Text #15

Max Range: 0.1543. Min Range: -0.1543

Max Act: 0.1070. Min Act: -0.0001

Data Index: 1304783 (C4 (Web Text))

Max Activating Token Index: 644

Text #16

Max Range: 0.1543. Min Range: -0.1543

Max Act: 0.1092. Min Act: -0.0001

Data Index: 627147 (C4 (Web Text))

Max Activating Token Index: 390

Text #17

Max Range: 0.1543. Min Range: -0.1543

Max Act: 0.1052. Min Act: -0.0001

Data Index: 907608 (C4 (Web Text))

Max Activating Token Index: 708

Text #18

Max Range: 0.1543. Min Range: -0.1543

Max Act: 0.1112. Min Act: -0.0001

Data Index: 1835 (C4 (Web Text))

Max Activating Token Index: 785

Text #19

Max Range: 0.1543. Min Range: -0.1543

Max Act: 0.1064. Min Act: -0.0001

Data Index: 195168 (C4 (Web Text))

Max Activating Token Index: 275