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

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

Neuron 4238 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: 2.1283. Min Range: -2.1283

Max Act: 2.1283. Min Act: -0.0000

Data Index: 367444 (C4 (Web Text))

Max Activating Token Index: 69

Text #1

Max Range: 2.1283. Min Range: -2.1283

Max Act: 1.7225. Min Act: -0.0000

Data Index: 611869 (C4 (Web Text))

Max Activating Token Index: 1005

Text #2

Max Range: 2.1283. Min Range: -2.1283

Max Act: 1.6825. Min Act: -0.0000

Data Index: 85483 (C4 (Web Text))

Max Activating Token Index: 301

Text #3

Max Range: 2.1283. Min Range: -2.1283

Max Act: 1.6327. Min Act: -0.0000

Data Index: 145983 (C4 (Web Text))

Max Activating Token Index: 245

Text #4

Max Range: 2.1283. Min Range: -2.1283

Max Act: 1.4284. Min Act: -0.0000

Data Index: 655135 (C4 (Web Text))

Max Activating Token Index: 19

Text #5

Max Range: 2.1283. Min Range: -2.1283

Max Act: 1.5029. Min Act: -0.0000

Data Index: 465991 (C4 (Web Text))

Max Activating Token Index: 134

Text #6

Max Range: 2.1283. Min Range: -2.1283

Max Act: 1.4095. Min Act: -0.0000

Data Index: 114110 (C4 (Web Text))

Max Activating Token Index: 743

Text #7

Max Range: 2.1283. Min Range: -2.1283

Max Act: 1.4793. Min Act: -0.0000

Data Index: 699326 (C4 (Web Text))

Max Activating Token Index: 41

Text #8

Max Range: 2.1283. Min Range: -2.1283

Max Act: 1.5403. Min Act: -0.0000

Data Index: 978823 (C4 (Web Text))

Max Activating Token Index: 880

Text #9

Max Range: 2.1283. Min Range: -2.1283

Max Act: 1.3407. Min Act: -0.0000

Data Index: 1169333 (C4 (Web Text))

Max Activating Token Index: 193

Text #10

Max Range: 2.1283. Min Range: -2.1283

Max Act: 1.3837. Min Act: -0.0000

Data Index: 1152666 (C4 (Web Text))

Max Activating Token Index: 748

Text #11

Max Range: 2.1283. Min Range: -2.1283

Max Act: 1.3707. Min Act: -0.0000

Data Index: 416722 (C4 (Web Text))

Max Activating Token Index: 354

Text #12

Max Range: 2.1283. Min Range: -2.1283

Max Act: 1.2757. Min Act: -0.0000

Data Index: 417793 (C4 (Web Text))

Max Activating Token Index: 737

Text #13

Max Range: 2.1283. Min Range: -2.1283

Max Act: 1.2783. Min Act: -0.0000

Data Index: 477934 (C4 (Web Text))

Max Activating Token Index: 490

Text #14

Max Range: 2.1283. Min Range: -2.1283

Max Act: 1.3369. Min Act: -0.0000

Data Index: 674859 (C4 (Web Text))

Max Activating Token Index: 338

Text #15

Max Range: 2.1283. Min Range: -2.1283

Max Act: 1.3204. Min Act: -0.0000

Data Index: 1416320 (Python Code)

Max Activating Token Index: 270

Text #16

Max Range: 2.1283. Min Range: -2.1283

Max Act: 1.3162. Min Act: -0.0000

Data Index: 1026107 (C4 (Web Text))

Max Activating Token Index: 224

Text #17

Max Range: 2.1283. Min Range: -2.1283

Max Act: 1.3833. Min Act: -0.0000

Data Index: 907272 (C4 (Web Text))

Max Activating Token Index: 549

Text #18

Max Range: 2.1283. Min Range: -2.1283

Max Act: 1.2843. Min Act: -0.0000

Data Index: 596897 (C4 (Web Text))

Max Activating Token Index: 784

Text #19

Max Range: 2.1283. Min Range: -2.1283

Max Act: 1.2213. Min Act: -0.0000

Data Index: 1403915 (Python Code)

Max Activating Token Index: 1006