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

Dataset: The Pile

Neuron 2625 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3273. Min Range: -0.3273

Max Act: 0.3261. Min Act: -0.0000

Data Index: 1931138 (The Pile)

Max Activating Token Index: 719

Text #1

Max Range: 0.3273. Min Range: -0.3273

Max Act: 0.3273. Min Act: -0.0000

Data Index: 1789223 (The Pile)

Max Activating Token Index: 998

Text #2

Max Range: 0.3273. Min Range: -0.3273

Max Act: 0.3074. Min Act: -0.0000

Data Index: 741686 (The Pile)

Max Activating Token Index: 959

Text #3

Max Range: 0.3273. Min Range: -0.3273

Max Act: 0.2988. Min Act: -0.0000

Data Index: 661898 (The Pile)

Max Activating Token Index: 793

Text #4

Max Range: 0.3273. Min Range: -0.3273

Max Act: 0.2837. Min Act: -0.0000

Data Index: 1615062 (The Pile)

Max Activating Token Index: 997

Text #5

Max Range: 0.3273. Min Range: -0.3273

Max Act: 0.2749. Min Act: -0.0000

Data Index: 388521 (The Pile)

Max Activating Token Index: 391

Text #6

Max Range: 0.3273. Min Range: -0.3273

Max Act: 0.2849. Min Act: -0.0000

Data Index: 1080131 (The Pile)

Max Activating Token Index: 591

Text #7

Max Range: 0.3273. Min Range: -0.3273

Max Act: 0.2606. Min Act: -0.0000

Data Index: 84925 (The Pile)

Max Activating Token Index: 598

Text #8

Max Range: 0.3273. Min Range: -0.3273

Max Act: 0.2872. Min Act: -0.0000

Data Index: 91143 (The Pile)

Max Activating Token Index: 941

Text #9

Max Range: 0.3273. Min Range: -0.3273

Max Act: 0.2640. Min Act: -0.0000

Data Index: 963958 (The Pile)

Max Activating Token Index: 1015

Text #10

Max Range: 0.3273. Min Range: -0.3273

Max Act: 0.2647. Min Act: -0.0000

Data Index: 78589 (The Pile)

Max Activating Token Index: 747

Text #11

Max Range: 0.3273. Min Range: -0.3273

Max Act: 0.2546. Min Act: -0.0000

Data Index: 1044411 (The Pile)

Max Activating Token Index: 868

Text #12

Max Range: 0.3273. Min Range: -0.3273

Max Act: 0.2537. Min Act: -0.0000

Data Index: 784032 (The Pile)

Max Activating Token Index: 906

Text #13

Max Range: 0.3273. Min Range: -0.3273

Max Act: 0.2573. Min Act: -0.0000

Data Index: 8491 (The Pile)

Max Activating Token Index: 705

Text #14

Max Range: 0.3273. Min Range: -0.3273

Max Act: 0.2615. Min Act: -0.0000

Data Index: 938979 (The Pile)

Max Activating Token Index: 379

Text #15

Max Range: 0.3273. Min Range: -0.3273

Max Act: 0.2636. Min Act: 0.0000

Data Index: 1826473 (The Pile)

Max Activating Token Index: 814

Text #16

Max Range: 0.3273. Min Range: -0.3273

Max Act: 0.2453. Min Act: -0.0000

Data Index: 300411 (The Pile)

Max Activating Token Index: 280

Text #17

Max Range: 0.3273. Min Range: -0.3273

Max Act: 0.2509. Min Act: -0.0000

Data Index: 821657 (The Pile)

Max Activating Token Index: 362

Text #18

Max Range: 0.3273. Min Range: -0.3273

Max Act: 0.2589. Min Act: -0.0000

Data Index: 1141345 (The Pile)

Max Activating Token Index: 668

Text #19

Max Range: 0.3273. Min Range: -0.3273

Max Act: 0.2541. Min Act: -0.0000

Data Index: 1148006 (The Pile)

Max Activating Token Index: 624