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

Dataset: The Pile

Neuron 924 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: 0.9917. Min Range: -0.9917

Max Act: 0.9917. Min Act: -0.0000

Data Index: 1555081 (The Pile)

Max Activating Token Index: 675

Text #1

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.7488. Min Act: -0.0000

Data Index: 1318940 (The Pile)

Max Activating Token Index: 954

Text #2

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.7705. Min Act: -0.0000

Data Index: 1897801 (The Pile)

Max Activating Token Index: 628

Text #3

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.7514. Min Act: -0.0000

Data Index: 264553 (The Pile)

Max Activating Token Index: 774

Text #4

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.7226. Min Act: -0.0000

Data Index: 752163 (The Pile)

Max Activating Token Index: 462

Text #5

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.6936. Min Act: -0.0000

Data Index: 1837023 (The Pile)

Max Activating Token Index: 513

Text #6

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.7069. Min Act: -0.0000

Data Index: 1498968 (The Pile)

Max Activating Token Index: 916

Text #7

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.6689. Min Act: -0.0000

Data Index: 967283 (The Pile)

Max Activating Token Index: 897

Text #8

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.6893. Min Act: -0.0000

Data Index: 1210932 (The Pile)

Max Activating Token Index: 686

Text #9

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.7288. Min Act: -0.0000

Data Index: 1947805 (The Pile)

Max Activating Token Index: 921

Text #10

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.6795. Min Act: -0.0000

Data Index: 789313 (The Pile)

Max Activating Token Index: 750

Text #11

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.6544. Min Act: -0.0000

Data Index: 1720062 (The Pile)

Max Activating Token Index: 603

Text #12

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.6317. Min Act: -0.0000

Data Index: 1737592 (The Pile)

Max Activating Token Index: 745

Text #13

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.6744. Min Act: -0.0000

Data Index: 1437350 (The Pile)

Max Activating Token Index: 819

Text #14

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.6723. Min Act: -0.0000

Data Index: 236312 (The Pile)

Max Activating Token Index: 553

Text #15

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.6441. Min Act: -0.0000

Data Index: 1233992 (The Pile)

Max Activating Token Index: 399

Text #16

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.6194. Min Act: -0.0000

Data Index: 1027539 (The Pile)

Max Activating Token Index: 36

Text #17

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.6570. Min Act: -0.0000

Data Index: 1419848 (The Pile)

Max Activating Token Index: 220

Text #18

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.6026. Min Act: -0.0000

Data Index: 1152319 (The Pile)

Max Activating Token Index: 495

Text #19

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.6587. Min Act: -0.0000

Data Index: 210838 (The Pile)

Max Activating Token Index: 662