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

Dataset: The Pile

Neuron 1764 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: 0.6586. Min Range: -0.6586

Max Act: 0.6474. Min Act: -0.0000

Data Index: 1025493 (The Pile)

Max Activating Token Index: 758

Text #1

Max Range: 0.6586. Min Range: -0.6586

Max Act: 0.6491. Min Act: -0.0000

Data Index: 789130 (The Pile)

Max Activating Token Index: 888

Text #2

Max Range: 0.6586. Min Range: -0.6586

Max Act: 0.6306. Min Act: -0.0000

Data Index: 736103 (The Pile)

Max Activating Token Index: 883

Text #3

Max Range: 0.6586. Min Range: -0.6586

Max Act: 0.5921. Min Act: -0.0000

Data Index: 1954326 (The Pile)

Max Activating Token Index: 676

Text #4

Max Range: 0.6586. Min Range: -0.6586

Max Act: 0.5946. Min Act: -0.0000

Data Index: 479082 (The Pile)

Max Activating Token Index: 729

Text #5

Max Range: 0.6586. Min Range: -0.6586

Max Act: 0.5974. Min Act: -0.0000

Data Index: 747216 (The Pile)

Max Activating Token Index: 805

Text #6

Max Range: 0.6586. Min Range: -0.6586

Max Act: 0.6376. Min Act: -0.0000

Data Index: 557938 (The Pile)

Max Activating Token Index: 496

Text #7

Max Range: 0.6586. Min Range: -0.6586

Max Act: 0.6247. Min Act: -0.0000

Data Index: 1364409 (The Pile)

Max Activating Token Index: 925

Text #8

Max Range: 0.6586. Min Range: -0.6586

Max Act: 0.5957. Min Act: -0.0000

Data Index: 536372 (The Pile)

Max Activating Token Index: 127

Text #9

Max Range: 0.6586. Min Range: -0.6586

Max Act: 0.6141. Min Act: -0.0000

Data Index: 1615552 (The Pile)

Max Activating Token Index: 949

Text #10

Max Range: 0.6586. Min Range: -0.6586

Max Act: 0.6336. Min Act: -0.0000

Data Index: 1029736 (The Pile)

Max Activating Token Index: 842

Text #11

Max Range: 0.6586. Min Range: -0.6586

Max Act: 0.5684. Min Act: -0.0000

Data Index: 1960658 (The Pile)

Max Activating Token Index: 609

Text #12

Max Range: 0.6586. Min Range: -0.6586

Max Act: 0.6586. Min Act: -0.0000

Data Index: 92496 (The Pile)

Max Activating Token Index: 540

Text #13

Max Range: 0.6586. Min Range: -0.6586

Max Act: 0.5874. Min Act: -0.0000

Data Index: 540718 (The Pile)

Max Activating Token Index: 456

Text #14

Max Range: 0.6586. Min Range: -0.6586

Max Act: 0.5666. Min Act: -0.0000

Data Index: 1168719 (The Pile)

Max Activating Token Index: 846

Text #15

Max Range: 0.6586. Min Range: -0.6586

Max Act: 0.5956. Min Act: -0.0000

Data Index: 1624532 (The Pile)

Max Activating Token Index: 732

Text #16

Max Range: 0.6586. Min Range: -0.6586

Max Act: 0.5685. Min Act: -0.0000

Data Index: 1743082 (The Pile)

Max Activating Token Index: 800

Text #17

Max Range: 0.6586. Min Range: -0.6586

Max Act: 0.5633. Min Act: -0.0000

Data Index: 1582288 (The Pile)

Max Activating Token Index: 280

Text #18

Max Range: 0.6586. Min Range: -0.6586

Max Act: 0.5847. Min Act: -0.0000

Data Index: 797801 (The Pile)

Max Activating Token Index: 459

Text #19

Max Range: 0.6586. Min Range: -0.6586

Max Act: 0.5756. Min Act: -0.0000

Data Index: 1042282 (The Pile)

Max Activating Token Index: 804