Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3255 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.6279. Min Range: -1.6279

Max Act: 1.6279. Min Act: -0.0001

Data Index: 1239286 (C4 (Web Text))

Max Activating Token Index: 404

Text #1

Max Range: 1.6279. Min Range: -1.6279

Max Act: 1.4184. Min Act: -0.0002

Data Index: 681055 (C4 (Web Text))

Max Activating Token Index: 932

Text #2

Max Range: 1.6279. Min Range: -1.6279

Max Act: 1.4031. Min Act: -0.0001

Data Index: 594713 (C4 (Web Text))

Max Activating Token Index: 918

Text #3

Max Range: 1.6279. Min Range: -1.6279

Max Act: 1.3548. Min Act: -0.0002

Data Index: 706502 (C4 (Web Text))

Max Activating Token Index: 105

Text #4

Max Range: 1.6279. Min Range: -1.6279

Max Act: 1.3520. Min Act: -0.0002

Data Index: 1206080 (C4 (Web Text))

Max Activating Token Index: 509

Text #5

Max Range: 1.6279. Min Range: -1.6279

Max Act: 1.4142. Min Act: -0.0001

Data Index: 695988 (C4 (Web Text))

Max Activating Token Index: 223

Text #6

Max Range: 1.6279. Min Range: -1.6279

Max Act: 1.3509. Min Act: -0.0001

Data Index: 16703 (C4 (Web Text))

Max Activating Token Index: 878

Text #7

Max Range: 1.6279. Min Range: -1.6279

Max Act: 1.3409. Min Act: -0.0001

Data Index: 1329056 (C4 (Web Text))

Max Activating Token Index: 210

Text #8

Max Range: 1.6279. Min Range: -1.6279

Max Act: 1.2815. Min Act: -0.0002

Data Index: 375104 (C4 (Web Text))

Max Activating Token Index: 206

Text #9

Max Range: 1.6279. Min Range: -1.6279

Max Act: 1.2957. Min Act: -0.0001

Data Index: 808899 (C4 (Web Text))

Max Activating Token Index: 739

Text #10

Max Range: 1.6279. Min Range: -1.6279

Max Act: 1.3293. Min Act: -0.0001

Data Index: 741544 (C4 (Web Text))

Max Activating Token Index: 466

Text #11

Max Range: 1.6279. Min Range: -1.6279

Max Act: 1.3135. Min Act: -0.0001

Data Index: 1347863 (C4 (Web Text))

Max Activating Token Index: 771

Text #12

Max Range: 1.6279. Min Range: -1.6279

Max Act: 1.2862. Min Act: -0.0001

Data Index: 566401 (C4 (Web Text))

Max Activating Token Index: 233

Text #13

Max Range: 1.6279. Min Range: -1.6279

Max Act: 1.2757. Min Act: -0.0001

Data Index: 704272 (C4 (Web Text))

Max Activating Token Index: 1002

Text #14

Max Range: 1.6279. Min Range: -1.6279

Max Act: 1.2713. Min Act: -0.0001

Data Index: 604117 (C4 (Web Text))

Max Activating Token Index: 994

Text #15

Max Range: 1.6279. Min Range: -1.6279

Max Act: 1.2360. Min Act: -0.0002

Data Index: 919621 (C4 (Web Text))

Max Activating Token Index: 389

Text #16

Max Range: 1.6279. Min Range: -1.6279

Max Act: 1.2607. Min Act: -0.0001

Data Index: 1257407 (C4 (Web Text))

Max Activating Token Index: 580

Text #17

Max Range: 1.6279. Min Range: -1.6279

Max Act: 1.2280. Min Act: -0.0001

Data Index: 194408 (C4 (Web Text))

Max Activating Token Index: 644

Text #18

Max Range: 1.6279. Min Range: -1.6279

Max Act: 1.2631. Min Act: -0.0001

Data Index: 1193809 (C4 (Web Text))

Max Activating Token Index: 112

Text #19

Max Range: 1.6279. Min Range: -1.6279

Max Act: 1.2525. Min Act: -0.0001

Data Index: 778197 (C4 (Web Text))

Max Activating Token Index: 267