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

Dataset: The Pile

Neuron 4550 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: 1.0977. Min Range: -1.0977

Max Act: 1.0261. Min Act: -0.0000

Data Index: 786631 (The Pile)

Max Activating Token Index: 246

Text #1

Max Range: 1.0977. Min Range: -1.0977

Max Act: 1.0977. Min Act: -0.0000

Data Index: 650741 (The Pile)

Max Activating Token Index: 150

Text #2

Max Range: 1.0977. Min Range: -1.0977

Max Act: 1.0368. Min Act: -0.0000

Data Index: 1882403 (The Pile)

Max Activating Token Index: 718

Text #3

Max Range: 1.0977. Min Range: -1.0977

Max Act: 0.8023. Min Act: -0.0000

Data Index: 742405 (The Pile)

Max Activating Token Index: 994

Text #4

Max Range: 1.0977. Min Range: -1.0977

Max Act: 0.9511. Min Act: -0.0000

Data Index: 738525 (The Pile)

Max Activating Token Index: 258

Text #5

Max Range: 1.0977. Min Range: -1.0977

Max Act: 0.7887. Min Act: -0.0000

Data Index: 817321 (The Pile)

Max Activating Token Index: 169

Text #6

Max Range: 1.0977. Min Range: -1.0977

Max Act: 0.8526. Min Act: -0.0000

Data Index: 1523485 (The Pile)

Max Activating Token Index: 58

Text #7

Max Range: 1.0977. Min Range: -1.0977

Max Act: 0.7589. Min Act: -0.0000

Data Index: 323424 (The Pile)

Max Activating Token Index: 877

Text #8

Max Range: 1.0977. Min Range: -1.0977

Max Act: 0.8052. Min Act: -0.0000

Data Index: 932375 (The Pile)

Max Activating Token Index: 656

Text #9

Max Range: 1.0977. Min Range: -1.0977

Max Act: 0.7899. Min Act: -0.0000

Data Index: 383150 (The Pile)

Max Activating Token Index: 759

Text #10

Max Range: 1.0977. Min Range: -1.0977

Max Act: 0.8039. Min Act: -0.0000

Data Index: 345807 (The Pile)

Max Activating Token Index: 741

Text #11

Max Range: 1.0977. Min Range: -1.0977

Max Act: 0.7163. Min Act: -0.0000

Data Index: 1624219 (The Pile)

Max Activating Token Index: 974

Text #12

Max Range: 1.0977. Min Range: -1.0977

Max Act: 0.6328. Min Act: -0.0000

Data Index: 1782840 (The Pile)

Max Activating Token Index: 985

Text #13

Max Range: 1.0977. Min Range: -1.0977

Max Act: 0.7091. Min Act: -0.0000

Data Index: 400822 (The Pile)

Max Activating Token Index: 526

Text #14

Max Range: 1.0977. Min Range: -1.0977

Max Act: 0.7313. Min Act: -0.0000

Data Index: 21765 (The Pile)

Max Activating Token Index: 707

Text #15

Max Range: 1.0977. Min Range: -1.0977

Max Act: 0.6528. Min Act: -0.0000

Data Index: 1107953 (The Pile)

Max Activating Token Index: 930

Text #16

Max Range: 1.0977. Min Range: -1.0977

Max Act: 0.6864. Min Act: -0.0000

Data Index: 1440705 (The Pile)

Max Activating Token Index: 505

Text #17

Max Range: 1.0977. Min Range: -1.0977

Max Act: 0.6145. Min Act: -0.0000

Data Index: 1793800 (The Pile)

Max Activating Token Index: 1001

Text #18

Max Range: 1.0977. Min Range: -1.0977

Max Act: 0.7039. Min Act: -0.0000

Data Index: 1421908 (The Pile)

Max Activating Token Index: 866

Text #19

Max Range: 1.0977. Min Range: -1.0977

Max Act: 0.7263. Min Act: -0.0000

Data Index: 46646 (The Pile)

Max Activating Token Index: 236