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

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

Neuron 2123 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1486. Min Act: -0.0001

Data Index: 92556 (C4 (Web Text))

Max Activating Token Index: 688

Text #1

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1452. Min Act: -0.0001

Data Index: 504936 (C4 (Web Text))

Max Activating Token Index: 382

Text #2

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1301. Min Act: -0.0001

Data Index: 35677 (C4 (Web Text))

Max Activating Token Index: 79

Text #3

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1370. Min Act: -0.0001

Data Index: 752187 (C4 (Web Text))

Max Activating Token Index: 261

Text #4

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1303. Min Act: -0.0001

Data Index: 885507 (C4 (Web Text))

Max Activating Token Index: 806

Text #5

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1313. Min Act: -0.0001

Data Index: 124831 (C4 (Web Text))

Max Activating Token Index: 443

Text #6

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1212. Min Act: -0.0001

Data Index: 1180522 (C4 (Web Text))

Max Activating Token Index: 33

Text #7

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1150. Min Act: -0.0001

Data Index: 1480306 (Python Code)

Max Activating Token Index: 942

Text #8

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1146. Min Act: -0.0001

Data Index: 290398 (C4 (Web Text))

Max Activating Token Index: 84

Text #9

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1149. Min Act: -0.0001

Data Index: 108454 (C4 (Web Text))

Max Activating Token Index: 196

Text #10

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1135. Min Act: -0.0001

Data Index: 1125372 (C4 (Web Text))

Max Activating Token Index: 74

Text #11

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1217. Min Act: -0.0001

Data Index: 659849 (C4 (Web Text))

Max Activating Token Index: 641

Text #12

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1175. Min Act: -0.0001

Data Index: 1283451 (C4 (Web Text))

Max Activating Token Index: 140

Text #13

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1208. Min Act: -0.0001

Data Index: 146052 (C4 (Web Text))

Max Activating Token Index: 214

Text #14

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1119. Min Act: -0.0001

Data Index: 751290 (C4 (Web Text))

Max Activating Token Index: 195

Text #15

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1105. Min Act: -0.0001

Data Index: 130977 (C4 (Web Text))

Max Activating Token Index: 91

Text #16

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1111. Min Act: -0.0000

Data Index: 532734 (C4 (Web Text))

Max Activating Token Index: 828

Text #17

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1078. Min Act: -0.0001

Data Index: 1210373 (C4 (Web Text))

Max Activating Token Index: 81

Text #18

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1108. Min Act: -0.0001

Data Index: 258527 (C4 (Web Text))

Max Activating Token Index: 127

Text #19

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1234. Min Act: -0.0001

Data Index: 294697 (C4 (Web Text))

Max Activating Token Index: 173