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

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

Neuron 207 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1241. Min Range: -3.1241

Max Act: 3.1228. Min Act: -0.0000

Data Index: 601530 (C4 (Web Text))

Max Activating Token Index: 980

Text #1

Max Range: 3.1241. Min Range: -3.1241

Max Act: 3.1241. Min Act: -0.0000

Data Index: 30619 (C4 (Web Text))

Max Activating Token Index: 850

Text #2

Max Range: 3.1241. Min Range: -3.1241

Max Act: 3.0400. Min Act: 0.0000

Data Index: 528038 (C4 (Web Text))

Max Activating Token Index: 691

Text #3

Max Range: 3.1241. Min Range: -3.1241

Max Act: 2.6650. Min Act: -0.0000

Data Index: 118620 (C4 (Web Text))

Max Activating Token Index: 248

Text #4

Max Range: 3.1241. Min Range: -3.1241

Max Act: 2.4349. Min Act: -0.0000

Data Index: 172911 (C4 (Web Text))

Max Activating Token Index: 1016

Text #5

Max Range: 3.1241. Min Range: -3.1241

Max Act: 2.3976. Min Act: -0.0000

Data Index: 304733 (C4 (Web Text))

Max Activating Token Index: 944

Text #6

Max Range: 3.1241. Min Range: -3.1241

Max Act: 2.3892. Min Act: -0.0000

Data Index: 1312181 (C4 (Web Text))

Max Activating Token Index: 450

Text #7

Max Range: 3.1241. Min Range: -3.1241

Max Act: 2.4595. Min Act: -0.0000

Data Index: 241743 (C4 (Web Text))

Max Activating Token Index: 873

Text #8

Max Range: 3.1241. Min Range: -3.1241

Max Act: 2.2856. Min Act: -0.0000

Data Index: 921524 (C4 (Web Text))

Max Activating Token Index: 435

Text #9

Max Range: 3.1241. Min Range: -3.1241

Max Act: 2.2268. Min Act: -0.0000

Data Index: 1086818 (C4 (Web Text))

Max Activating Token Index: 183

Text #10

Max Range: 3.1241. Min Range: -3.1241

Max Act: 2.2069. Min Act: -0.0000

Data Index: 670297 (C4 (Web Text))

Max Activating Token Index: 100

Text #11

Max Range: 3.1241. Min Range: -3.1241

Max Act: 2.1995. Min Act: -0.0000

Data Index: 912720 (C4 (Web Text))

Max Activating Token Index: 827

Text #12

Max Range: 3.1241. Min Range: -3.1241

Max Act: 2.2004. Min Act: -0.0000

Data Index: 264016 (C4 (Web Text))

Max Activating Token Index: 878

Text #13

Max Range: 3.1241. Min Range: -3.1241

Max Act: 2.0691. Min Act: -0.0000

Data Index: 738978 (C4 (Web Text))

Max Activating Token Index: 899

Text #14

Max Range: 3.1241. Min Range: -3.1241

Max Act: 2.0850. Min Act: -0.0000

Data Index: 333121 (C4 (Web Text))

Max Activating Token Index: 557

Text #15

Max Range: 3.1241. Min Range: -3.1241

Max Act: 2.1661. Min Act: -0.0000

Data Index: 370513 (C4 (Web Text))

Max Activating Token Index: 760

Text #16

Max Range: 3.1241. Min Range: -3.1241

Max Act: 2.1165. Min Act: -0.0000

Data Index: 307997 (C4 (Web Text))

Max Activating Token Index: 40

Text #17

Max Range: 3.1241. Min Range: -3.1241

Max Act: 2.0886. Min Act: -0.0000

Data Index: 480267 (C4 (Web Text))

Max Activating Token Index: 753

Text #18

Max Range: 3.1241. Min Range: -3.1241

Max Act: 1.9540. Min Act: -0.0000

Data Index: 624163 (C4 (Web Text))

Max Activating Token Index: 785

Text #19

Max Range: 3.1241. Min Range: -3.1241

Max Act: 2.0280. Min Act: -0.0000

Data Index: 405311 (C4 (Web Text))

Max Activating Token Index: 733