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

Dataset: The Pile

Neuron 3774 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4983. Min Range: -1.4983

Max Act: 1.4983. Min Act: -0.0000

Data Index: 397641 (The Pile)

Max Activating Token Index: 573

Text #1

Max Range: 1.4983. Min Range: -1.4983

Max Act: 1.3618. Min Act: -0.0000

Data Index: 1697637 (The Pile)

Max Activating Token Index: 831

Text #2

Max Range: 1.4983. Min Range: -1.4983

Max Act: 1.4382. Min Act: -0.0000

Data Index: 1291279 (The Pile)

Max Activating Token Index: 605

Text #3

Max Range: 1.4983. Min Range: -1.4983

Max Act: 1.3912. Min Act: -0.0000

Data Index: 1797887 (The Pile)

Max Activating Token Index: 517

Text #4

Max Range: 1.4983. Min Range: -1.4983

Max Act: 1.2494. Min Act: -0.0000

Data Index: 970322 (The Pile)

Max Activating Token Index: 911

Text #5

Max Range: 1.4983. Min Range: -1.4983

Max Act: 1.3895. Min Act: -0.0000

Data Index: 984558 (The Pile)

Max Activating Token Index: 525

Text #6

Max Range: 1.4983. Min Range: -1.4983

Max Act: 1.3864. Min Act: -0.0000

Data Index: 1576255 (The Pile)

Max Activating Token Index: 261

Text #7

Max Range: 1.4983. Min Range: -1.4983

Max Act: 1.2961. Min Act: -0.0000

Data Index: 1563931 (The Pile)

Max Activating Token Index: 153

Text #8

Max Range: 1.4983. Min Range: -1.4983

Max Act: 1.3585. Min Act: -0.0000

Data Index: 86867 (The Pile)

Max Activating Token Index: 805

Text #9

Max Range: 1.4983. Min Range: -1.4983

Max Act: 1.3312. Min Act: -0.0000

Data Index: 1864810 (The Pile)

Max Activating Token Index: 492

Text #10

Max Range: 1.4983. Min Range: -1.4983

Max Act: 1.3591. Min Act: -0.0000

Data Index: 70995 (The Pile)

Max Activating Token Index: 318

Text #11

Max Range: 1.4983. Min Range: -1.4983

Max Act: 1.3313. Min Act: -0.0000

Data Index: 1082525 (The Pile)

Max Activating Token Index: 1002

Text #12

Max Range: 1.4983. Min Range: -1.4983

Max Act: 1.3531. Min Act: -0.0000

Data Index: 56122 (The Pile)

Max Activating Token Index: 858

Text #13

Max Range: 1.4983. Min Range: -1.4983

Max Act: 1.2913. Min Act: -0.0000

Data Index: 604581 (The Pile)

Max Activating Token Index: 461

Text #14

Max Range: 1.4983. Min Range: -1.4983

Max Act: 1.3252. Min Act: -0.0000

Data Index: 1937299 (The Pile)

Max Activating Token Index: 230

Text #15

Max Range: 1.4983. Min Range: -1.4983

Max Act: 1.1800. Min Act: -0.0000

Data Index: 908374 (The Pile)

Max Activating Token Index: 156

Text #16

Max Range: 1.4983. Min Range: -1.4983

Max Act: 1.1911. Min Act: -0.0000

Data Index: 472672 (The Pile)

Max Activating Token Index: 745

Text #17

Max Range: 1.4983. Min Range: -1.4983

Max Act: 1.1759. Min Act: -0.0000

Data Index: 107394 (The Pile)

Max Activating Token Index: 250

Text #18

Max Range: 1.4983. Min Range: -1.4983

Max Act: 1.2037. Min Act: -0.0000

Data Index: 942110 (The Pile)

Max Activating Token Index: 493

Text #19

Max Range: 1.4983. Min Range: -1.4983

Max Act: 1.1835. Min Act: -0.0000

Data Index: 1355564 (The Pile)

Max Activating Token Index: 741