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

Dataset: The Pile

Neuron 3541 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: 1.0434. Min Range: -1.0434

Max Act: 0.9867. Min Act: -0.0000

Data Index: 1429716 (The Pile)

Max Activating Token Index: 955

Text #1

Max Range: 1.0434. Min Range: -1.0434

Max Act: 1.0434. Min Act: -0.0000

Data Index: 1757008 (The Pile)

Max Activating Token Index: 587

Text #2

Max Range: 1.0434. Min Range: -1.0434

Max Act: 1.0000. Min Act: -0.0000

Data Index: 1309216 (The Pile)

Max Activating Token Index: 980

Text #3

Max Range: 1.0434. Min Range: -1.0434

Max Act: 0.9681. Min Act: -0.0000

Data Index: 134385 (The Pile)

Max Activating Token Index: 760

Text #4

Max Range: 1.0434. Min Range: -1.0434

Max Act: 0.9847. Min Act: -0.0000

Data Index: 246457 (The Pile)

Max Activating Token Index: 806

Text #5

Max Range: 1.0434. Min Range: -1.0434

Max Act: 1.0217. Min Act: -0.0000

Data Index: 1553196 (The Pile)

Max Activating Token Index: 371

Text #6

Max Range: 1.0434. Min Range: -1.0434

Max Act: 0.9237. Min Act: -0.0000

Data Index: 1519126 (The Pile)

Max Activating Token Index: 794

Text #7

Max Range: 1.0434. Min Range: -1.0434

Max Act: 0.9536. Min Act: -0.0000

Data Index: 1594510 (The Pile)

Max Activating Token Index: 773

Text #8

Max Range: 1.0434. Min Range: -1.0434

Max Act: 0.9629. Min Act: -0.0000

Data Index: 1200680 (The Pile)

Max Activating Token Index: 951

Text #9

Max Range: 1.0434. Min Range: -1.0434

Max Act: 0.9328. Min Act: -0.0000

Data Index: 1539394 (The Pile)

Max Activating Token Index: 407

Text #10

Max Range: 1.0434. Min Range: -1.0434

Max Act: 0.9226. Min Act: -0.0000

Data Index: 956256 (The Pile)

Max Activating Token Index: 941

Text #11

Max Range: 1.0434. Min Range: -1.0434

Max Act: 0.9226. Min Act: -0.0000

Data Index: 11246 (The Pile)

Max Activating Token Index: 629

Text #12

Max Range: 1.0434. Min Range: -1.0434

Max Act: 0.9674. Min Act: -0.0000

Data Index: 1598928 (The Pile)

Max Activating Token Index: 451

Text #13

Max Range: 1.0434. Min Range: -1.0434

Max Act: 0.9143. Min Act: -0.0000

Data Index: 673483 (The Pile)

Max Activating Token Index: 617

Text #14

Max Range: 1.0434. Min Range: -1.0434

Max Act: 0.9344. Min Act: -0.0000

Data Index: 1042242 (The Pile)

Max Activating Token Index: 1000

Text #15

Max Range: 1.0434. Min Range: -1.0434

Max Act: 0.9699. Min Act: -0.0000

Data Index: 1363385 (The Pile)

Max Activating Token Index: 105

Text #16

Max Range: 1.0434. Min Range: -1.0434

Max Act: 0.9053. Min Act: -0.0000

Data Index: 136553 (The Pile)

Max Activating Token Index: 843

Text #17

Max Range: 1.0434. Min Range: -1.0434

Max Act: 0.9280. Min Act: -0.0000

Data Index: 1213712 (The Pile)

Max Activating Token Index: 718

Text #18

Max Range: 1.0434. Min Range: -1.0434

Max Act: 0.9309. Min Act: -0.0000

Data Index: 1016669 (The Pile)

Max Activating Token Index: 918

Text #19

Max Range: 1.0434. Min Range: -1.0434

Max Act: 0.9485. Min Act: -0.0000

Data Index: 1966817 (The Pile)

Max Activating Token Index: 883