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

Dataset: The Pile

Neuron 23 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: 1.1409. Min Range: -1.1409

Max Act: 1.0794. Min Act: -0.0000

Data Index: 102915 (The Pile)

Max Activating Token Index: 290

Text #1

Max Range: 1.1409. Min Range: -1.1409

Max Act: 1.1409. Min Act: -0.0000

Data Index: 259615 (The Pile)

Max Activating Token Index: 22

Text #2

Max Range: 1.1409. Min Range: -1.1409

Max Act: 0.9411. Min Act: -0.0000

Data Index: 69144 (The Pile)

Max Activating Token Index: 87

Text #3

Max Range: 1.1409. Min Range: -1.1409

Max Act: 0.9579. Min Act: -0.0000

Data Index: 381793 (The Pile)

Max Activating Token Index: 418

Text #4

Max Range: 1.1409. Min Range: -1.1409

Max Act: 0.8991. Min Act: -0.0000

Data Index: 731987 (The Pile)

Max Activating Token Index: 591

Text #5

Max Range: 1.1409. Min Range: -1.1409

Max Act: 0.8883. Min Act: -0.0000

Data Index: 1023369 (The Pile)

Max Activating Token Index: 967

Text #6

Max Range: 1.1409. Min Range: -1.1409

Max Act: 0.8868. Min Act: -0.0000

Data Index: 1382798 (The Pile)

Max Activating Token Index: 653

Text #7

Max Range: 1.1409. Min Range: -1.1409

Max Act: 0.9011. Min Act: -0.0000

Data Index: 732526 (The Pile)

Max Activating Token Index: 16

Text #8

Max Range: 1.1409. Min Range: -1.1409

Max Act: 0.9018. Min Act: -0.0000

Data Index: 1985361 (The Pile)

Max Activating Token Index: 917

Text #9

Max Range: 1.1409. Min Range: -1.1409

Max Act: 0.8593. Min Act: -0.0000

Data Index: 513381 (The Pile)

Max Activating Token Index: 982

Text #10

Max Range: 1.1409. Min Range: -1.1409

Max Act: 0.8072. Min Act: -0.0000

Data Index: 538839 (The Pile)

Max Activating Token Index: 793

Text #11

Max Range: 1.1409. Min Range: -1.1409

Max Act: 0.8265. Min Act: -0.0000

Data Index: 1006342 (The Pile)

Max Activating Token Index: 910

Text #12

Max Range: 1.1409. Min Range: -1.1409

Max Act: 0.8161. Min Act: -0.0000

Data Index: 317195 (The Pile)

Max Activating Token Index: 342

Text #13

Max Range: 1.1409. Min Range: -1.1409

Max Act: 0.8346. Min Act: -0.0000

Data Index: 1099687 (The Pile)

Max Activating Token Index: 598

Text #14

Max Range: 1.1409. Min Range: -1.1409

Max Act: 0.8483. Min Act: -0.0000

Data Index: 1355274 (The Pile)

Max Activating Token Index: 990

Text #15

Max Range: 1.1409. Min Range: -1.1409

Max Act: 0.7856. Min Act: -0.0000

Data Index: 1180949 (The Pile)

Max Activating Token Index: 958

Text #16

Max Range: 1.1409. Min Range: -1.1409

Max Act: 0.7845. Min Act: -0.0000

Data Index: 1063527 (The Pile)

Max Activating Token Index: 628

Text #17

Max Range: 1.1409. Min Range: -1.1409

Max Act: 0.8184. Min Act: -0.0000

Data Index: 1214203 (The Pile)

Max Activating Token Index: 191

Text #18

Max Range: 1.1409. Min Range: -1.1409

Max Act: 0.8264. Min Act: -0.0000

Data Index: 1115863 (The Pile)

Max Activating Token Index: 462

Text #19

Max Range: 1.1409. Min Range: -1.1409

Max Act: 0.7792. Min Act: -0.0000

Data Index: 1166840 (The Pile)

Max Activating Token Index: 1013