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

Dataset: The Pile

Neuron 762 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: 0.8554. Min Range: -0.8554

Max Act: 0.8554. Min Act: -0.0000

Data Index: 690688 (The Pile)

Max Activating Token Index: 175

Text #1

Max Range: 0.8554. Min Range: -0.8554

Max Act: 0.8400. Min Act: -0.0000

Data Index: 1712523 (The Pile)

Max Activating Token Index: 705

Text #2

Max Range: 0.8554. Min Range: -0.8554

Max Act: 0.7312. Min Act: -0.0000

Data Index: 1680614 (The Pile)

Max Activating Token Index: 834

Text #3

Max Range: 0.8554. Min Range: -0.8554

Max Act: 0.8335. Min Act: -0.0000

Data Index: 1282620 (The Pile)

Max Activating Token Index: 806

Text #4

Max Range: 0.8554. Min Range: -0.8554

Max Act: 0.8211. Min Act: -0.0000

Data Index: 1431849 (The Pile)

Max Activating Token Index: 89

Text #5

Max Range: 0.8554. Min Range: -0.8554

Max Act: 0.7220. Min Act: -0.0000

Data Index: 459724 (The Pile)

Max Activating Token Index: 783

Text #6

Max Range: 0.8554. Min Range: -0.8554

Max Act: 0.7228. Min Act: -0.0000

Data Index: 791263 (The Pile)

Max Activating Token Index: 1005

Text #7

Max Range: 0.8554. Min Range: -0.8554

Max Act: 0.7564. Min Act: -0.0000

Data Index: 1698803 (The Pile)

Max Activating Token Index: 681

Text #8

Max Range: 0.8554. Min Range: -0.8554

Max Act: 0.6897. Min Act: -0.0000

Data Index: 1522739 (The Pile)

Max Activating Token Index: 995

Text #9

Max Range: 0.8554. Min Range: -0.8554

Max Act: 0.6630. Min Act: -0.0000

Data Index: 1547926 (The Pile)

Max Activating Token Index: 792

Text #10

Max Range: 0.8554. Min Range: -0.8554

Max Act: 0.6635. Min Act: -0.0000

Data Index: 747897 (The Pile)

Max Activating Token Index: 916

Text #11

Max Range: 0.8554. Min Range: -0.8554

Max Act: 0.6875. Min Act: -0.0000

Data Index: 555263 (The Pile)

Max Activating Token Index: 235

Text #12

Max Range: 0.8554. Min Range: -0.8554

Max Act: 0.6751. Min Act: -0.0000

Data Index: 1772637 (The Pile)

Max Activating Token Index: 643

Text #13

Max Range: 0.8554. Min Range: -0.8554

Max Act: 0.6582. Min Act: -0.0000

Data Index: 1663448 (The Pile)

Max Activating Token Index: 362

Text #14

Max Range: 0.8554. Min Range: -0.8554

Max Act: 0.6584. Min Act: -0.0000

Data Index: 1873562 (The Pile)

Max Activating Token Index: 969

Text #15

Max Range: 0.8554. Min Range: -0.8554

Max Act: 0.7056. Min Act: -0.0000

Data Index: 1072470 (The Pile)

Max Activating Token Index: 577

Text #16

Max Range: 0.8554. Min Range: -0.8554

Max Act: 0.6403. Min Act: -0.0000

Data Index: 486382 (The Pile)

Max Activating Token Index: 541

Text #17

Max Range: 0.8554. Min Range: -0.8554

Max Act: 0.7136. Min Act: -0.0000

Data Index: 608658 (The Pile)

Max Activating Token Index: 907

Text #18

Max Range: 0.8554. Min Range: -0.8554

Max Act: 0.6248. Min Act: -0.0000

Data Index: 1313252 (The Pile)

Max Activating Token Index: 172

Text #19

Max Range: 0.8554. Min Range: -0.8554

Max Act: 0.6786. Min Act: -0.0000

Data Index: 498386 (The Pile)

Max Activating Token Index: 969