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

Dataset: The Pile

Neuron 269 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.4417. Min Range: -1.4417

Max Act: 1.4417. Min Act: -0.0000

Data Index: 205058 (The Pile)

Max Activating Token Index: 904

Text #1

Max Range: 1.4417. Min Range: -1.4417

Max Act: 1.4267. Min Act: -0.0000

Data Index: 549195 (The Pile)

Max Activating Token Index: 864

Text #2

Max Range: 1.4417. Min Range: -1.4417

Max Act: 1.3522. Min Act: -0.0000

Data Index: 727604 (The Pile)

Max Activating Token Index: 42

Text #3

Max Range: 1.4417. Min Range: -1.4417

Max Act: 1.3325. Min Act: -0.0000

Data Index: 241183 (The Pile)

Max Activating Token Index: 469

Text #4

Max Range: 1.4417. Min Range: -1.4417

Max Act: 1.2613. Min Act: -0.0000

Data Index: 552855 (The Pile)

Max Activating Token Index: 511

Text #5

Max Range: 1.4417. Min Range: -1.4417

Max Act: 1.0930. Min Act: -0.0000

Data Index: 1880536 (The Pile)

Max Activating Token Index: 567

Text #6

Max Range: 1.4417. Min Range: -1.4417

Max Act: 1.1590. Min Act: -0.0000

Data Index: 1928205 (The Pile)

Max Activating Token Index: 285

Text #7

Max Range: 1.4417. Min Range: -1.4417

Max Act: 1.0755. Min Act: -0.0000

Data Index: 1041242 (The Pile)

Max Activating Token Index: 471

Text #8

Max Range: 1.4417. Min Range: -1.4417

Max Act: 1.0513. Min Act: -0.0000

Data Index: 679775 (The Pile)

Max Activating Token Index: 284

Text #9

Max Range: 1.4417. Min Range: -1.4417

Max Act: 1.0740. Min Act: -0.0000

Data Index: 303475 (The Pile)

Max Activating Token Index: 453

Text #10

Max Range: 1.4417. Min Range: -1.4417

Max Act: 1.0455. Min Act: -0.0000

Data Index: 581701 (The Pile)

Max Activating Token Index: 155

Text #11

Max Range: 1.4417. Min Range: -1.4417

Max Act: 1.0757. Min Act: -0.0000

Data Index: 535413 (The Pile)

Max Activating Token Index: 418

Text #12

Max Range: 1.4417. Min Range: -1.4417

Max Act: 1.0087. Min Act: -0.0000

Data Index: 1089561 (The Pile)

Max Activating Token Index: 156

Text #13

Max Range: 1.4417. Min Range: -1.4417

Max Act: 0.9447. Min Act: -0.0000

Data Index: 904211 (The Pile)

Max Activating Token Index: 656

Text #14

Max Range: 1.4417. Min Range: -1.4417

Max Act: 1.0255. Min Act: -0.0000

Data Index: 1319097 (The Pile)

Max Activating Token Index: 955

Text #15

Max Range: 1.4417. Min Range: -1.4417

Max Act: 1.0485. Min Act: -0.0000

Data Index: 1399302 (The Pile)

Max Activating Token Index: 204

Text #16

Max Range: 1.4417. Min Range: -1.4417

Max Act: 0.9252. Min Act: -0.0000

Data Index: 1157017 (The Pile)

Max Activating Token Index: 831

Text #17

Max Range: 1.4417. Min Range: -1.4417

Max Act: 0.9200. Min Act: -0.0000

Data Index: 1349762 (The Pile)

Max Activating Token Index: 540

Text #18

Max Range: 1.4417. Min Range: -1.4417

Max Act: 0.9315. Min Act: -0.0000

Data Index: 411079 (The Pile)

Max Activating Token Index: 505

Text #19

Max Range: 1.4417. Min Range: -1.4417

Max Act: 0.9727. Min Act: -0.0000

Data Index: 1070805 (The Pile)

Max Activating Token Index: 13