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

Dataset: The Pile

Neuron 394 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: 0.7735. Min Range: -0.7735

Max Act: 0.7735. Min Act: -0.0000

Data Index: 1552280 (The Pile)

Max Activating Token Index: 389

Text #1

Max Range: 0.7735. Min Range: -0.7735

Max Act: 0.7427. Min Act: -0.0000

Data Index: 388372 (The Pile)

Max Activating Token Index: 521

Text #2

Max Range: 0.7735. Min Range: -0.7735

Max Act: 0.7423. Min Act: -0.0000

Data Index: 573760 (The Pile)

Max Activating Token Index: 634

Text #3

Max Range: 0.7735. Min Range: -0.7735

Max Act: 0.6820. Min Act: -0.0000

Data Index: 1127216 (The Pile)

Max Activating Token Index: 427

Text #4

Max Range: 0.7735. Min Range: -0.7735

Max Act: 0.6475. Min Act: -0.0000

Data Index: 319768 (The Pile)

Max Activating Token Index: 948

Text #5

Max Range: 0.7735. Min Range: -0.7735

Max Act: 0.6472. Min Act: -0.0000

Data Index: 619379 (The Pile)

Max Activating Token Index: 941

Text #6

Max Range: 0.7735. Min Range: -0.7735

Max Act: 0.6232. Min Act: -0.0000

Data Index: 1297406 (The Pile)

Max Activating Token Index: 658

Text #7

Max Range: 0.7735. Min Range: -0.7735

Max Act: 0.5827. Min Act: -0.0000

Data Index: 1576421 (The Pile)

Max Activating Token Index: 304

Text #8

Max Range: 0.7735. Min Range: -0.7735

Max Act: 0.6204. Min Act: -0.0000

Data Index: 1814412 (The Pile)

Max Activating Token Index: 101

Text #9

Max Range: 0.7735. Min Range: -0.7735

Max Act: 0.6031. Min Act: -0.0000

Data Index: 1193935 (The Pile)

Max Activating Token Index: 179

Text #10

Max Range: 0.7735. Min Range: -0.7735

Max Act: 0.5839. Min Act: -0.0000

Data Index: 949425 (The Pile)

Max Activating Token Index: 577

Text #11

Max Range: 0.7735. Min Range: -0.7735

Max Act: 0.5798. Min Act: -0.0000

Data Index: 1924809 (The Pile)

Max Activating Token Index: 964

Text #12

Max Range: 0.7735. Min Range: -0.7735

Max Act: 0.5622. Min Act: -0.0000

Data Index: 1176508 (The Pile)

Max Activating Token Index: 56

Text #13

Max Range: 0.7735. Min Range: -0.7735

Max Act: 0.5787. Min Act: -0.0000

Data Index: 879592 (The Pile)

Max Activating Token Index: 659

Text #14

Max Range: 0.7735. Min Range: -0.7735

Max Act: 0.5662. Min Act: -0.0000

Data Index: 1141709 (The Pile)

Max Activating Token Index: 147

Text #15

Max Range: 0.7735. Min Range: -0.7735

Max Act: 0.5396. Min Act: -0.0000

Data Index: 647994 (The Pile)

Max Activating Token Index: 402

Text #16

Max Range: 0.7735. Min Range: -0.7735

Max Act: 0.5754. Min Act: -0.0000

Data Index: 899755 (The Pile)

Max Activating Token Index: 675

Text #17

Max Range: 0.7735. Min Range: -0.7735

Max Act: 0.5535. Min Act: -0.0000

Data Index: 1903785 (The Pile)

Max Activating Token Index: 822

Text #18

Max Range: 0.7735. Min Range: -0.7735

Max Act: 0.6054. Min Act: -0.0000

Data Index: 105488 (The Pile)

Max Activating Token Index: 935

Text #19

Max Range: 0.7735. Min Range: -0.7735

Max Act: 0.5448. Min Act: -0.0000

Data Index: 1694806 (The Pile)

Max Activating Token Index: 470