Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 1745 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 4.7961. Min Range: -4.7961

Max Act: 4.7961. Min Act: -0.0000

Data Index: 1845651 (The Pile)

Max Activating Token Index: 873

Text #1

Max Range: 4.7961. Min Range: -4.7961

Max Act: 4.4163. Min Act: -0.0000

Data Index: 871701 (The Pile)

Max Activating Token Index: 342

Text #2

Max Range: 4.7961. Min Range: -4.7961

Max Act: 4.0268. Min Act: -0.0000

Data Index: 891473 (The Pile)

Max Activating Token Index: 635

Text #3

Max Range: 4.7961. Min Range: -4.7961

Max Act: 3.8644. Min Act: -0.0000

Data Index: 789195 (The Pile)

Max Activating Token Index: 668

Text #4

Max Range: 4.7961. Min Range: -4.7961

Max Act: 3.7695. Min Act: -0.0000

Data Index: 678108 (The Pile)

Max Activating Token Index: 1009

Text #5

Max Range: 4.7961. Min Range: -4.7961

Max Act: 3.9227. Min Act: -0.0000

Data Index: 876526 (The Pile)

Max Activating Token Index: 516

Text #6

Max Range: 4.7961. Min Range: -4.7961

Max Act: 3.9242. Min Act: -0.0000

Data Index: 1992695 (The Pile)

Max Activating Token Index: 505

Text #7

Max Range: 4.7961. Min Range: -4.7961

Max Act: 3.9042. Min Act: -0.0000

Data Index: 1985541 (The Pile)

Max Activating Token Index: 304

Text #8

Max Range: 4.7961. Min Range: -4.7961

Max Act: 3.7449. Min Act: -0.0000

Data Index: 597769 (The Pile)

Max Activating Token Index: 24

Text #9

Max Range: 4.7961. Min Range: -4.7961

Max Act: 3.9565. Min Act: -0.0000

Data Index: 1511966 (The Pile)

Max Activating Token Index: 896

Text #10

Max Range: 4.7961. Min Range: -4.7961

Max Act: 3.7692. Min Act: -0.0000

Data Index: 1927769 (The Pile)

Max Activating Token Index: 923

Text #11

Max Range: 4.7961. Min Range: -4.7961

Max Act: 3.6311. Min Act: -0.0000

Data Index: 1577199 (The Pile)

Max Activating Token Index: 730

Text #12

Max Range: 4.7961. Min Range: -4.7961

Max Act: 3.7665. Min Act: -0.0000

Data Index: 607039 (The Pile)

Max Activating Token Index: 140

Text #13

Max Range: 4.7961. Min Range: -4.7961

Max Act: 3.7780. Min Act: -0.0000

Data Index: 1806713 (The Pile)

Max Activating Token Index: 428

Text #14

Max Range: 4.7961. Min Range: -4.7961

Max Act: 3.7260. Min Act: -0.0000

Data Index: 617521 (The Pile)

Max Activating Token Index: 380

Text #15

Max Range: 4.7961. Min Range: -4.7961

Max Act: 3.8764. Min Act: -0.0000

Data Index: 1274885 (The Pile)

Max Activating Token Index: 397

Text #16

Max Range: 4.7961. Min Range: -4.7961

Max Act: 3.7100. Min Act: -0.0000

Data Index: 1267527 (The Pile)

Max Activating Token Index: 98

Text #17

Max Range: 4.7961. Min Range: -4.7961

Max Act: 3.6677. Min Act: -0.0000

Data Index: 921474 (The Pile)

Max Activating Token Index: 27

Text #18

Max Range: 4.7961. Min Range: -4.7961

Max Act: 3.6644. Min Act: -0.0000

Data Index: 972428 (The Pile)

Max Activating Token Index: 719

Text #19

Max Range: 4.7961. Min Range: -4.7961

Max Act: 3.6503. Min Act: -0.0000

Data Index: 1976420 (The Pile)

Max Activating Token Index: 973