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

Dataset: The Pile

Neuron 2960 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0471. Min Range: -1.0471

Max Act: 1.0471. Min Act: -0.0000

Data Index: 1184662 (The Pile)

Max Activating Token Index: 995

Text #1

Max Range: 1.0471. Min Range: -1.0471

Max Act: 0.9850. Min Act: -0.0000

Data Index: 1113586 (The Pile)

Max Activating Token Index: 568

Text #2

Max Range: 1.0471. Min Range: -1.0471

Max Act: 0.9649. Min Act: -0.0000

Data Index: 1723422 (The Pile)

Max Activating Token Index: 621

Text #3

Max Range: 1.0471. Min Range: -1.0471

Max Act: 0.9822. Min Act: -0.0000

Data Index: 467821 (The Pile)

Max Activating Token Index: 964

Text #4

Max Range: 1.0471. Min Range: -1.0471

Max Act: 0.9117. Min Act: -0.0000

Data Index: 1567395 (The Pile)

Max Activating Token Index: 162

Text #5

Max Range: 1.0471. Min Range: -1.0471

Max Act: 0.8864. Min Act: -0.0000

Data Index: 1875643 (The Pile)

Max Activating Token Index: 519

Text #6

Max Range: 1.0471. Min Range: -1.0471

Max Act: 0.9544. Min Act: -0.0000

Data Index: 1402921 (The Pile)

Max Activating Token Index: 411

Text #7

Max Range: 1.0471. Min Range: -1.0471

Max Act: 0.9094. Min Act: -0.0000

Data Index: 59642 (The Pile)

Max Activating Token Index: 228

Text #8

Max Range: 1.0471. Min Range: -1.0471

Max Act: 0.8763. Min Act: -0.0000

Data Index: 1947758 (The Pile)

Max Activating Token Index: 42

Text #9

Max Range: 1.0471. Min Range: -1.0471

Max Act: 0.8674. Min Act: -0.0000

Data Index: 486845 (The Pile)

Max Activating Token Index: 611

Text #10

Max Range: 1.0471. Min Range: -1.0471

Max Act: 0.8878. Min Act: -0.0000

Data Index: 1139777 (The Pile)

Max Activating Token Index: 629

Text #11

Max Range: 1.0471. Min Range: -1.0471

Max Act: 0.8522. Min Act: -0.0000

Data Index: 1059190 (The Pile)

Max Activating Token Index: 990

Text #12

Max Range: 1.0471. Min Range: -1.0471

Max Act: 0.8731. Min Act: -0.0000

Data Index: 1827837 (The Pile)

Max Activating Token Index: 461

Text #13

Max Range: 1.0471. Min Range: -1.0471

Max Act: 0.8355. Min Act: -0.0000

Data Index: 105307 (The Pile)

Max Activating Token Index: 535

Text #14

Max Range: 1.0471. Min Range: -1.0471

Max Act: 0.8586. Min Act: -0.0000

Data Index: 1790548 (The Pile)

Max Activating Token Index: 204

Text #15

Max Range: 1.0471. Min Range: -1.0471

Max Act: 0.8555. Min Act: -0.0000

Data Index: 945455 (The Pile)

Max Activating Token Index: 495

Text #16

Max Range: 1.0471. Min Range: -1.0471

Max Act: 0.8380. Min Act: -0.0000

Data Index: 598276 (The Pile)

Max Activating Token Index: 185

Text #17

Max Range: 1.0471. Min Range: -1.0471

Max Act: 0.8139. Min Act: -0.0000

Data Index: 1114401 (The Pile)

Max Activating Token Index: 665

Text #18

Max Range: 1.0471. Min Range: -1.0471

Max Act: 0.7765. Min Act: -0.0000

Data Index: 1988944 (The Pile)

Max Activating Token Index: 769

Text #19

Max Range: 1.0471. Min Range: -1.0471

Max Act: 0.8269. Min Act: -0.0000

Data Index: 1605922 (The Pile)

Max Activating Token Index: 162