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

Dataset: The Pile

Neuron 3912 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3351. Min Range: -5.3351

Max Act: 5.3351. Min Act: -0.0000

Data Index: 302776 (The Pile)

Max Activating Token Index: 489

Text #1

Max Range: 5.3351. Min Range: -5.3351

Max Act: 5.2928. Min Act: -0.0000

Data Index: 1625173 (The Pile)

Max Activating Token Index: 484

Text #2

Max Range: 5.3351. Min Range: -5.3351

Max Act: 4.7133. Min Act: -0.0000

Data Index: 566704 (The Pile)

Max Activating Token Index: 622

Text #3

Max Range: 5.3351. Min Range: -5.3351

Max Act: 5.0030. Min Act: -0.0000

Data Index: 537687 (The Pile)

Max Activating Token Index: 581

Text #4

Max Range: 5.3351. Min Range: -5.3351

Max Act: 4.7654. Min Act: -0.0000

Data Index: 796923 (The Pile)

Max Activating Token Index: 413

Text #5

Max Range: 5.3351. Min Range: -5.3351

Max Act: 4.5078. Min Act: -0.0000

Data Index: 17336 (The Pile)

Max Activating Token Index: 270

Text #6

Max Range: 5.3351. Min Range: -5.3351

Max Act: 4.8424. Min Act: -0.0000

Data Index: 654885 (The Pile)

Max Activating Token Index: 294

Text #7

Max Range: 5.3351. Min Range: -5.3351

Max Act: 4.3749. Min Act: -0.0000

Data Index: 1490084 (The Pile)

Max Activating Token Index: 253

Text #8

Max Range: 5.3351. Min Range: -5.3351

Max Act: 3.8704. Min Act: -0.0000

Data Index: 1282513 (The Pile)

Max Activating Token Index: 643

Text #9

Max Range: 5.3351. Min Range: -5.3351

Max Act: 4.2210. Min Act: -0.0000

Data Index: 1317186 (The Pile)

Max Activating Token Index: 568

Text #10

Max Range: 5.3351. Min Range: -5.3351

Max Act: 4.1593. Min Act: -0.0000

Data Index: 58447 (The Pile)

Max Activating Token Index: 724

Text #11

Max Range: 5.3351. Min Range: -5.3351

Max Act: 4.2636. Min Act: -0.0000

Data Index: 508835 (The Pile)

Max Activating Token Index: 541

Text #12

Max Range: 5.3351. Min Range: -5.3351

Max Act: 3.9365. Min Act: -0.0000

Data Index: 629021 (The Pile)

Max Activating Token Index: 156

Text #13

Max Range: 5.3351. Min Range: -5.3351

Max Act: 4.1204. Min Act: -0.0000

Data Index: 1094281 (The Pile)

Max Activating Token Index: 100

Text #14

Max Range: 5.3351. Min Range: -5.3351

Max Act: 4.1012. Min Act: -0.0000

Data Index: 727879 (The Pile)

Max Activating Token Index: 633

Text #15

Max Range: 5.3351. Min Range: -5.3351

Max Act: 3.9579. Min Act: -0.0000

Data Index: 1594301 (The Pile)

Max Activating Token Index: 423

Text #16

Max Range: 5.3351. Min Range: -5.3351

Max Act: 4.1110. Min Act: -0.0000

Data Index: 1635894 (The Pile)

Max Activating Token Index: 389

Text #17

Max Range: 5.3351. Min Range: -5.3351

Max Act: 4.0609. Min Act: -0.0000

Data Index: 1508838 (The Pile)

Max Activating Token Index: 281

Text #18

Max Range: 5.3351. Min Range: -5.3351

Max Act: 3.7280. Min Act: -0.0000

Data Index: 1167472 (The Pile)

Max Activating Token Index: 185

Text #19

Max Range: 5.3351. Min Range: -5.3351

Max Act: 3.7203. Min Act: -0.0000

Data Index: 1319386 (The Pile)

Max Activating Token Index: 906