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

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

Neuron 1835 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0183. Min Range: -2.0183

Max Act: 2.0183. Min Act: -0.0001

Data Index: 860371 (C4 (Web Text))

Max Activating Token Index: 87

Text #1

Max Range: 2.0183. Min Range: -2.0183

Max Act: 1.7433. Min Act: -0.0000

Data Index: 825976 (C4 (Web Text))

Max Activating Token Index: 328

Text #2

Max Range: 2.0183. Min Range: -2.0183

Max Act: 1.6820. Min Act: -0.0000

Data Index: 273915 (C4 (Web Text))

Max Activating Token Index: 674

Text #3

Max Range: 2.0183. Min Range: -2.0183

Max Act: 1.8410. Min Act: -0.0000

Data Index: 236838 (C4 (Web Text))

Max Activating Token Index: 197

Text #4

Max Range: 2.0183. Min Range: -2.0183

Max Act: 1.5455. Min Act: -0.0000

Data Index: 627232 (C4 (Web Text))

Max Activating Token Index: 744

Text #5

Max Range: 2.0183. Min Range: -2.0183

Max Act: 1.6230. Min Act: -0.0000

Data Index: 1114450 (C4 (Web Text))

Max Activating Token Index: 273

Text #6

Max Range: 2.0183. Min Range: -2.0183

Max Act: 1.5225. Min Act: -0.0000

Data Index: 322607 (C4 (Web Text))

Max Activating Token Index: 247

Text #7

Max Range: 2.0183. Min Range: -2.0183

Max Act: 1.5524. Min Act: -0.0001

Data Index: 619751 (C4 (Web Text))

Max Activating Token Index: 815

Text #8

Max Range: 2.0183. Min Range: -2.0183

Max Act: 1.3523. Min Act: -0.0000

Data Index: 357129 (C4 (Web Text))

Max Activating Token Index: 491

Text #9

Max Range: 2.0183. Min Range: -2.0183

Max Act: 1.4064. Min Act: -0.0000

Data Index: 59300 (C4 (Web Text))

Max Activating Token Index: 395

Text #10

Max Range: 2.0183. Min Range: -2.0183

Max Act: 1.4036. Min Act: -0.0000

Data Index: 389613 (C4 (Web Text))

Max Activating Token Index: 374

Text #11

Max Range: 2.0183. Min Range: -2.0183

Max Act: 1.4036. Min Act: -0.0000

Data Index: 368440 (C4 (Web Text))

Max Activating Token Index: 599

Text #12

Max Range: 2.0183. Min Range: -2.0183

Max Act: 1.3741. Min Act: -0.0000

Data Index: 1357161 (C4 (Web Text))

Max Activating Token Index: 890

Text #13

Max Range: 2.0183. Min Range: -2.0183

Max Act: 1.3446. Min Act: -0.0000

Data Index: 990607 (C4 (Web Text))

Max Activating Token Index: 795

Text #14

Max Range: 2.0183. Min Range: -2.0183

Max Act: 1.4222. Min Act: -0.0000

Data Index: 330440 (C4 (Web Text))

Max Activating Token Index: 220

Text #15

Max Range: 2.0183. Min Range: -2.0183

Max Act: 1.1817. Min Act: -0.0000

Data Index: 138827 (C4 (Web Text))

Max Activating Token Index: 787

Text #16

Max Range: 2.0183. Min Range: -2.0183

Max Act: 1.3159. Min Act: -0.0000

Data Index: 1191567 (C4 (Web Text))

Max Activating Token Index: 960

Text #17

Max Range: 2.0183. Min Range: -2.0183

Max Act: 1.3149. Min Act: -0.0000

Data Index: 343016 (C4 (Web Text))

Max Activating Token Index: 10

Text #18

Max Range: 2.0183. Min Range: -2.0183

Max Act: 1.3612. Min Act: -0.0000

Data Index: 1101414 (C4 (Web Text))

Max Activating Token Index: 879

Text #19

Max Range: 2.0183. Min Range: -2.0183

Max Act: 1.2773. Min Act: -0.0000

Data Index: 1065059 (C4 (Web Text))

Max Activating Token Index: 612