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

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

Neuron 1592 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1388. Min Act: -0.0001

Data Index: 501328 (C4 (Web Text))

Max Activating Token Index: 369

Text #1

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1509. Min Act: -0.0001

Data Index: 504095 (C4 (Web Text))

Max Activating Token Index: 485

Text #2

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1380. Min Act: -0.0001

Data Index: 250477 (C4 (Web Text))

Max Activating Token Index: 177

Text #3

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1153. Min Act: -0.0001

Data Index: 1294931 (C4 (Web Text))

Max Activating Token Index: 791

Text #4

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1304. Min Act: -0.0001

Data Index: 13907 (C4 (Web Text))

Max Activating Token Index: 399

Text #5

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1224. Min Act: -0.0001

Data Index: 321896 (C4 (Web Text))

Max Activating Token Index: 149

Text #6

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1320. Min Act: -0.0001

Data Index: 487017 (C4 (Web Text))

Max Activating Token Index: 984

Text #7

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1054. Min Act: -0.0001

Data Index: 367171 (C4 (Web Text))

Max Activating Token Index: 183

Text #8

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1213. Min Act: -0.0000

Data Index: 1060974 (C4 (Web Text))

Max Activating Token Index: 373

Text #9

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1100. Min Act: -0.0000

Data Index: 1076281 (C4 (Web Text))

Max Activating Token Index: 801

Text #10

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1291. Min Act: -0.0001

Data Index: 885726 (C4 (Web Text))

Max Activating Token Index: 91

Text #11

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1250. Min Act: -0.0001

Data Index: 1189390 (C4 (Web Text))

Max Activating Token Index: 956

Text #12

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1195. Min Act: -0.0000

Data Index: 914257 (C4 (Web Text))

Max Activating Token Index: 335

Text #13

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1301. Min Act: -0.0001

Data Index: 939420 (C4 (Web Text))

Max Activating Token Index: 19

Text #14

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1185. Min Act: -0.0001

Data Index: 154746 (C4 (Web Text))

Max Activating Token Index: 937

Text #15

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1074. Min Act: -0.0001

Data Index: 786076 (C4 (Web Text))

Max Activating Token Index: 226

Text #16

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1240. Min Act: -0.0000

Data Index: 233670 (C4 (Web Text))

Max Activating Token Index: 95

Text #17

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1252. Min Act: -0.0000

Data Index: 1243493 (C4 (Web Text))

Max Activating Token Index: 523

Text #18

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1096. Min Act: -0.0001

Data Index: 716819 (C4 (Web Text))

Max Activating Token Index: 738

Text #19

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1291. Min Act: -0.0001

Data Index: 1157875 (C4 (Web Text))

Max Activating Token Index: 599