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

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

Neuron 2529 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: 0.1494. Min Range: -0.1494

Max Act: 0.1478. Min Act: -0.0000

Data Index: 1167814 (C4 (Web Text))

Max Activating Token Index: 361

Text #1

Max Range: 0.1494. Min Range: -0.1494

Max Act: 0.1371. Min Act: -0.0000

Data Index: 505898 (C4 (Web Text))

Max Activating Token Index: 926

Text #2

Max Range: 0.1494. Min Range: -0.1494

Max Act: 0.1494. Min Act: -0.0000

Data Index: 1295167 (C4 (Web Text))

Max Activating Token Index: 249

Text #3

Max Range: 0.1494. Min Range: -0.1494

Max Act: 0.1340. Min Act: -0.0000

Data Index: 810267 (C4 (Web Text))

Max Activating Token Index: 361

Text #4

Max Range: 0.1494. Min Range: -0.1494

Max Act: 0.1206. Min Act: -0.0000

Data Index: 707634 (C4 (Web Text))

Max Activating Token Index: 932

Text #5

Max Range: 0.1494. Min Range: -0.1494

Max Act: 0.1252. Min Act: -0.0000

Data Index: 1192127 (C4 (Web Text))

Max Activating Token Index: 597

Text #6

Max Range: 0.1494. Min Range: -0.1494

Max Act: 0.1321. Min Act: -0.0000

Data Index: 795014 (C4 (Web Text))

Max Activating Token Index: 170

Text #7

Max Range: 0.1494. Min Range: -0.1494

Max Act: 0.1162. Min Act: -0.0000

Data Index: 330057 (C4 (Web Text))

Max Activating Token Index: 333

Text #8

Max Range: 0.1494. Min Range: -0.1494

Max Act: 0.1149. Min Act: -0.0000

Data Index: 204398 (C4 (Web Text))

Max Activating Token Index: 614

Text #9

Max Range: 0.1494. Min Range: -0.1494

Max Act: 0.1181. Min Act: -0.0000

Data Index: 791196 (C4 (Web Text))

Max Activating Token Index: 338

Text #10

Max Range: 0.1494. Min Range: -0.1494

Max Act: 0.1254. Min Act: -0.0000

Data Index: 84561 (C4 (Web Text))

Max Activating Token Index: 317

Text #11

Max Range: 0.1494. Min Range: -0.1494

Max Act: 0.1153. Min Act: -0.0000

Data Index: 1461174 (Python Code)

Max Activating Token Index: 75

Text #12

Max Range: 0.1494. Min Range: -0.1494

Max Act: 0.1258. Min Act: -0.0000

Data Index: 950576 (C4 (Web Text))

Max Activating Token Index: 536

Text #13

Max Range: 0.1494. Min Range: -0.1494

Max Act: 0.1129. Min Act: -0.0000

Data Index: 810879 (C4 (Web Text))

Max Activating Token Index: 525

Text #14

Max Range: 0.1494. Min Range: -0.1494

Max Act: 0.1155. Min Act: -0.0000

Data Index: 914172 (C4 (Web Text))

Max Activating Token Index: 562

Text #15

Max Range: 0.1494. Min Range: -0.1494

Max Act: 0.1218. Min Act: -0.0001

Data Index: 777104 (C4 (Web Text))

Max Activating Token Index: 636

Text #16

Max Range: 0.1494. Min Range: -0.1494

Max Act: 0.1125. Min Act: -0.0000

Data Index: 1549078 (Python Code)

Max Activating Token Index: 38

Text #17

Max Range: 0.1494. Min Range: -0.1494

Max Act: 0.1167. Min Act: -0.0000

Data Index: 220608 (C4 (Web Text))

Max Activating Token Index: 107

Text #18

Max Range: 0.1494. Min Range: -0.1494

Max Act: 0.1103. Min Act: -0.0000

Data Index: 857281 (C4 (Web Text))

Max Activating Token Index: 65

Text #19

Max Range: 0.1494. Min Range: -0.1494

Max Act: 0.1130. Min Act: -0.0000

Data Index: 359543 (C4 (Web Text))

Max Activating Token Index: 667