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

Dataset: The Pile

Neuron 3085 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3447. Min Range: -1.3447

Max Act: 1.3447. Min Act: -0.0000

Data Index: 579105 (The Pile)

Max Activating Token Index: 847

Text #1

Max Range: 1.3447. Min Range: -1.3447

Max Act: 1.1225. Min Act: -0.0000

Data Index: 1731916 (The Pile)

Max Activating Token Index: 534

Text #2

Max Range: 1.3447. Min Range: -1.3447

Max Act: 0.9242. Min Act: 0.0000

Data Index: 998420 (The Pile)

Max Activating Token Index: 586

Text #3

Max Range: 1.3447. Min Range: -1.3447

Max Act: 0.9515. Min Act: -0.0000

Data Index: 1611603 (The Pile)

Max Activating Token Index: 176

Text #4

Max Range: 1.3447. Min Range: -1.3447

Max Act: 0.8580. Min Act: -0.0000

Data Index: 643533 (The Pile)

Max Activating Token Index: 321

Text #5

Max Range: 1.3447. Min Range: -1.3447

Max Act: 0.8599. Min Act: -0.0000

Data Index: 794026 (The Pile)

Max Activating Token Index: 113

Text #6

Max Range: 1.3447. Min Range: -1.3447

Max Act: 0.8347. Min Act: -0.0000

Data Index: 1547072 (The Pile)

Max Activating Token Index: 88

Text #7

Max Range: 1.3447. Min Range: -1.3447

Max Act: 0.8803. Min Act: -0.0000

Data Index: 53968 (The Pile)

Max Activating Token Index: 356

Text #8

Max Range: 1.3447. Min Range: -1.3447

Max Act: 0.8110. Min Act: -0.0000

Data Index: 1866597 (The Pile)

Max Activating Token Index: 397

Text #9

Max Range: 1.3447. Min Range: -1.3447

Max Act: 0.7504. Min Act: -0.0000

Data Index: 340771 (The Pile)

Max Activating Token Index: 397

Text #10

Max Range: 1.3447. Min Range: -1.3447

Max Act: 0.8310. Min Act: -0.0000

Data Index: 1328162 (The Pile)

Max Activating Token Index: 48

Text #11

Max Range: 1.3447. Min Range: -1.3447

Max Act: 0.8259. Min Act: -0.0000

Data Index: 1967198 (The Pile)

Max Activating Token Index: 906

Text #12

Max Range: 1.3447. Min Range: -1.3447

Max Act: 0.8445. Min Act: -0.0000

Data Index: 1293651 (The Pile)

Max Activating Token Index: 869

Text #13

Max Range: 1.3447. Min Range: -1.3447

Max Act: 0.8150. Min Act: -0.0000

Data Index: 1565279 (The Pile)

Max Activating Token Index: 582

Text #14

Max Range: 1.3447. Min Range: -1.3447

Max Act: 0.7858. Min Act: -0.0000

Data Index: 535899 (The Pile)

Max Activating Token Index: 691

Text #15

Max Range: 1.3447. Min Range: -1.3447

Max Act: 0.7630. Min Act: -0.0000

Data Index: 1592195 (The Pile)

Max Activating Token Index: 1016

Text #16

Max Range: 1.3447. Min Range: -1.3447

Max Act: 0.7832. Min Act: -0.0000

Data Index: 1679135 (The Pile)

Max Activating Token Index: 822

Text #17

Max Range: 1.3447. Min Range: -1.3447

Max Act: 0.7826. Min Act: -0.0000

Data Index: 382906 (The Pile)

Max Activating Token Index: 540

Text #18

Max Range: 1.3447. Min Range: -1.3447

Max Act: 0.6805. Min Act: -0.0000

Data Index: 617474 (The Pile)

Max Activating Token Index: 818

Text #19

Max Range: 1.3447. Min Range: -1.3447

Max Act: 0.7718. Min Act: -0.0000

Data Index: 80244 (The Pile)

Max Activating Token Index: 161