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

Dataset: The Pile

Neuron 1170 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.4098. Min Range: -0.4098

Max Act: 0.4098. Min Act: -0.0000

Data Index: 526934 (The Pile)

Max Activating Token Index: 960

Text #1

Max Range: 0.4098. Min Range: -0.4098

Max Act: 0.3419. Min Act: -0.0000

Data Index: 662258 (The Pile)

Max Activating Token Index: 908

Text #2

Max Range: 0.4098. Min Range: -0.4098

Max Act: 0.3254. Min Act: -0.0000

Data Index: 878442 (The Pile)

Max Activating Token Index: 517

Text #3

Max Range: 0.4098. Min Range: -0.4098

Max Act: 0.3004. Min Act: -0.0000

Data Index: 1565 (The Pile)

Max Activating Token Index: 172

Text #4

Max Range: 0.4098. Min Range: -0.4098

Max Act: 0.2995. Min Act: -0.0000

Data Index: 1371034 (The Pile)

Max Activating Token Index: 929

Text #5

Max Range: 0.4098. Min Range: -0.4098

Max Act: 0.3056. Min Act: -0.0000

Data Index: 932385 (The Pile)

Max Activating Token Index: 638

Text #6

Max Range: 0.4098. Min Range: -0.4098

Max Act: 0.2960. Min Act: -0.0000

Data Index: 183747 (The Pile)

Max Activating Token Index: 136

Text #7

Max Range: 0.4098. Min Range: -0.4098

Max Act: 0.2959. Min Act: -0.0000

Data Index: 1973582 (The Pile)

Max Activating Token Index: 881

Text #8

Max Range: 0.4098. Min Range: -0.4098

Max Act: 0.2730. Min Act: -0.0000

Data Index: 1339219 (The Pile)

Max Activating Token Index: 453

Text #9

Max Range: 0.4098. Min Range: -0.4098

Max Act: 0.2831. Min Act: -0.0000

Data Index: 19032 (The Pile)

Max Activating Token Index: 302

Text #10

Max Range: 0.4098. Min Range: -0.4098

Max Act: 0.2786. Min Act: -0.0000

Data Index: 584593 (The Pile)

Max Activating Token Index: 887

Text #11

Max Range: 0.4098. Min Range: -0.4098

Max Act: 0.2730. Min Act: -0.0000

Data Index: 1402280 (The Pile)

Max Activating Token Index: 848

Text #12

Max Range: 0.4098. Min Range: -0.4098

Max Act: 0.2672. Min Act: -0.0000

Data Index: 1021458 (The Pile)

Max Activating Token Index: 843

Text #13

Max Range: 0.4098. Min Range: -0.4098

Max Act: 0.2838. Min Act: -0.0000

Data Index: 278472 (The Pile)

Max Activating Token Index: 643

Text #14

Max Range: 0.4098. Min Range: -0.4098

Max Act: 0.2632. Min Act: -0.0000

Data Index: 347459 (The Pile)

Max Activating Token Index: 1004

Text #15

Max Range: 0.4098. Min Range: -0.4098

Max Act: 0.2598. Min Act: -0.0000

Data Index: 1860564 (The Pile)

Max Activating Token Index: 255

Text #16

Max Range: 0.4098. Min Range: -0.4098

Max Act: 0.2653. Min Act: -0.0000

Data Index: 1788493 (The Pile)

Max Activating Token Index: 294

Text #17

Max Range: 0.4098. Min Range: -0.4098

Max Act: 0.2542. Min Act: -0.0000

Data Index: 952646 (The Pile)

Max Activating Token Index: 391

Text #18

Max Range: 0.4098. Min Range: -0.4098

Max Act: 0.2613. Min Act: -0.0000

Data Index: 1831428 (The Pile)

Max Activating Token Index: 440

Text #19

Max Range: 0.4098. Min Range: -0.4098

Max Act: 0.2444. Min Act: -0.0000

Data Index: 435243 (The Pile)

Max Activating Token Index: 317