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

Dataset: The Pile

Neuron 3183 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: 0.9575. Min Range: -0.9575

Max Act: 0.9575. Min Act: -0.0000

Data Index: 1560842 (The Pile)

Max Activating Token Index: 24

Text #1

Max Range: 0.9575. Min Range: -0.9575

Max Act: 0.7259. Min Act: -0.0000

Data Index: 1869858 (The Pile)

Max Activating Token Index: 322

Text #2

Max Range: 0.9575. Min Range: -0.9575

Max Act: 0.6717. Min Act: -0.0000

Data Index: 757589 (The Pile)

Max Activating Token Index: 957

Text #3

Max Range: 0.9575. Min Range: -0.9575

Max Act: 0.6527. Min Act: -0.0000

Data Index: 1787442 (The Pile)

Max Activating Token Index: 20

Text #4

Max Range: 0.9575. Min Range: -0.9575

Max Act: 0.6655. Min Act: -0.0000

Data Index: 914214 (The Pile)

Max Activating Token Index: 847

Text #5

Max Range: 0.9575. Min Range: -0.9575

Max Act: 0.5896. Min Act: -0.0000

Data Index: 1979627 (The Pile)

Max Activating Token Index: 793

Text #6

Max Range: 0.9575. Min Range: -0.9575

Max Act: 0.6456. Min Act: -0.0000

Data Index: 1887507 (The Pile)

Max Activating Token Index: 53

Text #7

Max Range: 0.9575. Min Range: -0.9575

Max Act: 0.5853. Min Act: -0.0000

Data Index: 574323 (The Pile)

Max Activating Token Index: 956

Text #8

Max Range: 0.9575. Min Range: -0.9575

Max Act: 0.5576. Min Act: -0.0000

Data Index: 1396948 (The Pile)

Max Activating Token Index: 993

Text #9

Max Range: 0.9575. Min Range: -0.9575

Max Act: 0.5783. Min Act: -0.0000

Data Index: 1849245 (The Pile)

Max Activating Token Index: 116

Text #10

Max Range: 0.9575. Min Range: -0.9575

Max Act: 0.5865. Min Act: -0.0000

Data Index: 1870836 (The Pile)

Max Activating Token Index: 13

Text #11

Max Range: 0.9575. Min Range: -0.9575

Max Act: 0.5797. Min Act: -0.0000

Data Index: 493556 (The Pile)

Max Activating Token Index: 68

Text #12

Max Range: 0.9575. Min Range: -0.9575

Max Act: 0.5972. Min Act: -0.0000

Data Index: 490227 (The Pile)

Max Activating Token Index: 855

Text #13

Max Range: 0.9575. Min Range: -0.9575

Max Act: 0.5704. Min Act: -0.0000

Data Index: 1137541 (The Pile)

Max Activating Token Index: 43

Text #14

Max Range: 0.9575. Min Range: -0.9575

Max Act: 0.5668. Min Act: -0.0000

Data Index: 29360 (The Pile)

Max Activating Token Index: 150

Text #15

Max Range: 0.9575. Min Range: -0.9575

Max Act: 0.5435. Min Act: -0.0000

Data Index: 940997 (The Pile)

Max Activating Token Index: 1023

Text #16

Max Range: 0.9575. Min Range: -0.9575

Max Act: 0.5847. Min Act: -0.0000

Data Index: 260485 (The Pile)

Max Activating Token Index: 619

Text #17

Max Range: 0.9575. Min Range: -0.9575

Max Act: 0.5420. Min Act: -0.0000

Data Index: 1502246 (The Pile)

Max Activating Token Index: 572

Text #18

Max Range: 0.9575. Min Range: -0.9575

Max Act: 0.5533. Min Act: -0.0000

Data Index: 778701 (The Pile)

Max Activating Token Index: 246

Text #19

Max Range: 0.9575. Min Range: -0.9575

Max Act: 0.5524. Min Act: -0.0000

Data Index: 1160357 (The Pile)

Max Activating Token Index: 277