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

Dataset: The Pile

Neuron 3426 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6618. Min Range: -1.6618

Max Act: 1.6618. Min Act: -0.0000

Data Index: 377725 (The Pile)

Max Activating Token Index: 476

Text #1

Max Range: 1.6618. Min Range: -1.6618

Max Act: 1.5738. Min Act: -0.0000

Data Index: 320421 (The Pile)

Max Activating Token Index: 258

Text #2

Max Range: 1.6618. Min Range: -1.6618

Max Act: 1.5656. Min Act: -0.0000

Data Index: 916312 (The Pile)

Max Activating Token Index: 990

Text #3

Max Range: 1.6618. Min Range: -1.6618

Max Act: 1.4897. Min Act: -0.0000

Data Index: 438272 (The Pile)

Max Activating Token Index: 719

Text #4

Max Range: 1.6618. Min Range: -1.6618

Max Act: 1.4796. Min Act: -0.0000

Data Index: 1500283 (The Pile)

Max Activating Token Index: 38

Text #5

Max Range: 1.6618. Min Range: -1.6618

Max Act: 1.3665. Min Act: -0.0000

Data Index: 1179956 (The Pile)

Max Activating Token Index: 340

Text #6

Max Range: 1.6618. Min Range: -1.6618

Max Act: 1.5244. Min Act: -0.0000

Data Index: 137969 (The Pile)

Max Activating Token Index: 615

Text #7

Max Range: 1.6618. Min Range: -1.6618

Max Act: 1.3659. Min Act: -0.0000

Data Index: 1228425 (The Pile)

Max Activating Token Index: 925

Text #8

Max Range: 1.6618. Min Range: -1.6618

Max Act: 1.3655. Min Act: -0.0000

Data Index: 1483542 (The Pile)

Max Activating Token Index: 411

Text #9

Max Range: 1.6618. Min Range: -1.6618

Max Act: 1.3082. Min Act: -0.0000

Data Index: 457879 (The Pile)

Max Activating Token Index: 335

Text #10

Max Range: 1.6618. Min Range: -1.6618

Max Act: 1.1657. Min Act: -0.0000

Data Index: 1302914 (The Pile)

Max Activating Token Index: 188

Text #11

Max Range: 1.6618. Min Range: -1.6618

Max Act: 1.2986. Min Act: -0.0000

Data Index: 694105 (The Pile)

Max Activating Token Index: 640

Text #12

Max Range: 1.6618. Min Range: -1.6618

Max Act: 1.1884. Min Act: -0.0000

Data Index: 645012 (The Pile)

Max Activating Token Index: 549

Text #13

Max Range: 1.6618. Min Range: -1.6618

Max Act: 1.2042. Min Act: -0.0000

Data Index: 1707154 (The Pile)

Max Activating Token Index: 536

Text #14

Max Range: 1.6618. Min Range: -1.6618

Max Act: 1.0876. Min Act: -0.0000

Data Index: 517699 (The Pile)

Max Activating Token Index: 507

Text #15

Max Range: 1.6618. Min Range: -1.6618

Max Act: 1.1246. Min Act: -0.0000

Data Index: 649012 (The Pile)

Max Activating Token Index: 119

Text #16

Max Range: 1.6618. Min Range: -1.6618

Max Act: 1.0078. Min Act: -0.0000

Data Index: 874165 (The Pile)

Max Activating Token Index: 170

Text #17

Max Range: 1.6618. Min Range: -1.6618

Max Act: 1.0138. Min Act: -0.0000

Data Index: 1348069 (The Pile)

Max Activating Token Index: 532

Text #18

Max Range: 1.6618. Min Range: -1.6618

Max Act: 1.1351. Min Act: -0.0000

Data Index: 1339356 (The Pile)

Max Activating Token Index: 826

Text #19

Max Range: 1.6618. Min Range: -1.6618

Max Act: 1.0573. Min Act: -0.0000

Data Index: 772419 (The Pile)

Max Activating Token Index: 106