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

Dataset: The Pile

Neuron 2622 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3118. Min Range: -0.3118

Max Act: 0.3090. Min Act: -0.0000

Data Index: 855446 (The Pile)

Max Activating Token Index: 687

Text #1

Max Range: 0.3118. Min Range: -0.3118

Max Act: 0.3112. Min Act: -0.0000

Data Index: 679838 (The Pile)

Max Activating Token Index: 409

Text #2

Max Range: 0.3118. Min Range: -0.3118

Max Act: 0.3118. Min Act: -0.0000

Data Index: 732007 (The Pile)

Max Activating Token Index: 452

Text #3

Max Range: 0.3118. Min Range: -0.3118

Max Act: 0.2912. Min Act: -0.0000

Data Index: 1116991 (The Pile)

Max Activating Token Index: 515

Text #4

Max Range: 0.3118. Min Range: -0.3118

Max Act: 0.2570. Min Act: -0.0000

Data Index: 1337407 (The Pile)

Max Activating Token Index: 937

Text #5

Max Range: 0.3118. Min Range: -0.3118

Max Act: 0.2766. Min Act: -0.0000

Data Index: 1136389 (The Pile)

Max Activating Token Index: 406

Text #6

Max Range: 0.3118. Min Range: -0.3118

Max Act: 0.2748. Min Act: -0.0000

Data Index: 1145029 (The Pile)

Max Activating Token Index: 865

Text #7

Max Range: 0.3118. Min Range: -0.3118

Max Act: 0.2645. Min Act: -0.0000

Data Index: 446875 (The Pile)

Max Activating Token Index: 410

Text #8

Max Range: 0.3118. Min Range: -0.3118

Max Act: 0.2507. Min Act: -0.0000

Data Index: 1763768 (The Pile)

Max Activating Token Index: 480

Text #9

Max Range: 0.3118. Min Range: -0.3118

Max Act: 0.2540. Min Act: -0.0000

Data Index: 1641842 (The Pile)

Max Activating Token Index: 329

Text #10

Max Range: 0.3118. Min Range: -0.3118

Max Act: 0.2438. Min Act: -0.0000

Data Index: 753833 (The Pile)

Max Activating Token Index: 604

Text #11

Max Range: 0.3118. Min Range: -0.3118

Max Act: 0.2540. Min Act: -0.0000

Data Index: 1914883 (The Pile)

Max Activating Token Index: 619

Text #12

Max Range: 0.3118. Min Range: -0.3118

Max Act: 0.2530. Min Act: -0.0000

Data Index: 758855 (The Pile)

Max Activating Token Index: 393

Text #13

Max Range: 0.3118. Min Range: -0.3118

Max Act: 0.2601. Min Act: -0.0000

Data Index: 1285170 (The Pile)

Max Activating Token Index: 527

Text #14

Max Range: 0.3118. Min Range: -0.3118

Max Act: 0.2532. Min Act: -0.0000

Data Index: 1136976 (The Pile)

Max Activating Token Index: 692

Text #15

Max Range: 0.3118. Min Range: -0.3118

Max Act: 0.2522. Min Act: -0.0000

Data Index: 1166524 (The Pile)

Max Activating Token Index: 956

Text #16

Max Range: 0.3118. Min Range: -0.3118

Max Act: 0.2521. Min Act: -0.0000

Data Index: 1328387 (The Pile)

Max Activating Token Index: 437

Text #17

Max Range: 0.3118. Min Range: -0.3118

Max Act: 0.2347. Min Act: -0.0000

Data Index: 431648 (The Pile)

Max Activating Token Index: 784

Text #18

Max Range: 0.3118. Min Range: -0.3118

Max Act: 0.2416. Min Act: -0.0000

Data Index: 942012 (The Pile)

Max Activating Token Index: 923

Text #19

Max Range: 0.3118. Min Range: -0.3118

Max Act: 0.2458. Min Act: -0.0000

Data Index: 1864094 (The Pile)

Max Activating Token Index: 711