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

Dataset: The Pile

Neuron 179 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1876. Min Range: -1.1876

Max Act: 1.1876. Min Act: -0.0000

Data Index: 330823 (The Pile)

Max Activating Token Index: 345

Text #1

Max Range: 1.1876. Min Range: -1.1876

Max Act: 0.9913. Min Act: -0.0000

Data Index: 877344 (The Pile)

Max Activating Token Index: 879

Text #2

Max Range: 1.1876. Min Range: -1.1876

Max Act: 1.0946. Min Act: -0.0000

Data Index: 1386383 (The Pile)

Max Activating Token Index: 637

Text #3

Max Range: 1.1876. Min Range: -1.1876

Max Act: 0.9499. Min Act: -0.0000

Data Index: 453462 (The Pile)

Max Activating Token Index: 953

Text #4

Max Range: 1.1876. Min Range: -1.1876

Max Act: 0.9821. Min Act: -0.0000

Data Index: 1923635 (The Pile)

Max Activating Token Index: 888

Text #5

Max Range: 1.1876. Min Range: -1.1876

Max Act: 0.9834. Min Act: -0.0000

Data Index: 947060 (The Pile)

Max Activating Token Index: 331

Text #6

Max Range: 1.1876. Min Range: -1.1876

Max Act: 0.8697. Min Act: -0.0000

Data Index: 559660 (The Pile)

Max Activating Token Index: 966

Text #7

Max Range: 1.1876. Min Range: -1.1876

Max Act: 0.8527. Min Act: -0.0000

Data Index: 835154 (The Pile)

Max Activating Token Index: 90

Text #8

Max Range: 1.1876. Min Range: -1.1876

Max Act: 0.9565. Min Act: -0.0000

Data Index: 1007865 (The Pile)

Max Activating Token Index: 814

Text #9

Max Range: 1.1876. Min Range: -1.1876

Max Act: 0.9114. Min Act: -0.0000

Data Index: 500314 (The Pile)

Max Activating Token Index: 952

Text #10

Max Range: 1.1876. Min Range: -1.1876

Max Act: 0.9280. Min Act: -0.0000

Data Index: 309663 (The Pile)

Max Activating Token Index: 707

Text #11

Max Range: 1.1876. Min Range: -1.1876

Max Act: 0.8549. Min Act: -0.0000

Data Index: 1032547 (The Pile)

Max Activating Token Index: 453

Text #12

Max Range: 1.1876. Min Range: -1.1876

Max Act: 0.8320. Min Act: -0.0000

Data Index: 597814 (The Pile)

Max Activating Token Index: 560

Text #13

Max Range: 1.1876. Min Range: -1.1876

Max Act: 0.8585. Min Act: -0.0000

Data Index: 577901 (The Pile)

Max Activating Token Index: 456

Text #14

Max Range: 1.1876. Min Range: -1.1876

Max Act: 0.9434. Min Act: -0.0000

Data Index: 168294 (The Pile)

Max Activating Token Index: 1001

Text #15

Max Range: 1.1876. Min Range: -1.1876

Max Act: 0.9158. Min Act: -0.0000

Data Index: 1766599 (The Pile)

Max Activating Token Index: 413

Text #16

Max Range: 1.1876. Min Range: -1.1876

Max Act: 0.8437. Min Act: -0.0000

Data Index: 1303220 (The Pile)

Max Activating Token Index: 941

Text #17

Max Range: 1.1876. Min Range: -1.1876

Max Act: 0.8623. Min Act: -0.0000

Data Index: 1288799 (The Pile)

Max Activating Token Index: 348

Text #18

Max Range: 1.1876. Min Range: -1.1876

Max Act: 0.8770. Min Act: -0.0000

Data Index: 433464 (The Pile)

Max Activating Token Index: 1011

Text #19

Max Range: 1.1876. Min Range: -1.1876

Max Act: 0.7707. Min Act: -0.0000

Data Index: 1067579 (The Pile)

Max Activating Token Index: 894