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

Dataset: The Pile

Neuron 2566 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: 0.9077. Min Range: -0.9077

Max Act: 0.9077. Min Act: -0.0000

Data Index: 1530056 (The Pile)

Max Activating Token Index: 266

Text #1

Max Range: 0.9077. Min Range: -0.9077

Max Act: 0.8944. Min Act: -0.0000

Data Index: 849777 (The Pile)

Max Activating Token Index: 957

Text #2

Max Range: 0.9077. Min Range: -0.9077

Max Act: 0.8507. Min Act: -0.0000

Data Index: 1869188 (The Pile)

Max Activating Token Index: 343

Text #3

Max Range: 0.9077. Min Range: -0.9077

Max Act: 0.8446. Min Act: -0.0000

Data Index: 429614 (The Pile)

Max Activating Token Index: 219

Text #4

Max Range: 0.9077. Min Range: -0.9077

Max Act: 0.8524. Min Act: -0.0000

Data Index: 1627508 (The Pile)

Max Activating Token Index: 338

Text #5

Max Range: 0.9077. Min Range: -0.9077

Max Act: 0.8998. Min Act: -0.0000

Data Index: 1175259 (The Pile)

Max Activating Token Index: 585

Text #6

Max Range: 0.9077. Min Range: -0.9077

Max Act: 0.8388. Min Act: -0.0000

Data Index: 87293 (The Pile)

Max Activating Token Index: 557

Text #7

Max Range: 0.9077. Min Range: -0.9077

Max Act: 0.8578. Min Act: -0.0000

Data Index: 1379942 (The Pile)

Max Activating Token Index: 574

Text #8

Max Range: 0.9077. Min Range: -0.9077

Max Act: 0.8438. Min Act: -0.0000

Data Index: 1407595 (The Pile)

Max Activating Token Index: 345

Text #9

Max Range: 0.9077. Min Range: -0.9077

Max Act: 0.7622. Min Act: 0.0000

Data Index: 891455 (The Pile)

Max Activating Token Index: 1013

Text #10

Max Range: 0.9077. Min Range: -0.9077

Max Act: 0.8195. Min Act: -0.0000

Data Index: 1343950 (The Pile)

Max Activating Token Index: 402

Text #11

Max Range: 0.9077. Min Range: -0.9077

Max Act: 0.7973. Min Act: -0.0000

Data Index: 1033795 (The Pile)

Max Activating Token Index: 892

Text #12

Max Range: 0.9077. Min Range: -0.9077

Max Act: 0.7719. Min Act: -0.0000

Data Index: 1929199 (The Pile)

Max Activating Token Index: 30

Text #13

Max Range: 0.9077. Min Range: -0.9077

Max Act: 0.7730. Min Act: -0.0000

Data Index: 539831 (The Pile)

Max Activating Token Index: 156

Text #14

Max Range: 0.9077. Min Range: -0.9077

Max Act: 0.6782. Min Act: -0.0000

Data Index: 193606 (The Pile)

Max Activating Token Index: 825

Text #15

Max Range: 0.9077. Min Range: -0.9077

Max Act: 0.7372. Min Act: -0.0000

Data Index: 659391 (The Pile)

Max Activating Token Index: 948

Text #16

Max Range: 0.9077. Min Range: -0.9077

Max Act: 0.7536. Min Act: -0.0000

Data Index: 249409 (The Pile)

Max Activating Token Index: 657

Text #17

Max Range: 0.9077. Min Range: -0.9077

Max Act: 0.7404. Min Act: -0.0000

Data Index: 761029 (The Pile)

Max Activating Token Index: 114

Text #18

Max Range: 0.9077. Min Range: -0.9077

Max Act: 0.7374. Min Act: -0.0000

Data Index: 1794150 (The Pile)

Max Activating Token Index: 961

Text #19

Max Range: 0.9077. Min Range: -0.9077

Max Act: 0.7341. Min Act: -0.0000

Data Index: 1295596 (The Pile)

Max Activating Token Index: 1019