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

Dataset: The Pile

Neuron 3391 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: 0.3403. Min Range: -0.3403

Max Act: 0.3403. Min Act: -0.0000

Data Index: 204812 (The Pile)

Max Activating Token Index: 689

Text #1

Max Range: 0.3403. Min Range: -0.3403

Max Act: 0.3048. Min Act: -0.0000

Data Index: 1346515 (The Pile)

Max Activating Token Index: 392

Text #2

Max Range: 0.3403. Min Range: -0.3403

Max Act: 0.2875. Min Act: -0.0000

Data Index: 493135 (The Pile)

Max Activating Token Index: 659

Text #3

Max Range: 0.3403. Min Range: -0.3403

Max Act: 0.2946. Min Act: -0.0000

Data Index: 345237 (The Pile)

Max Activating Token Index: 990

Text #4

Max Range: 0.3403. Min Range: -0.3403

Max Act: 0.2694. Min Act: -0.0000

Data Index: 1335400 (The Pile)

Max Activating Token Index: 865

Text #5

Max Range: 0.3403. Min Range: -0.3403

Max Act: 0.2734. Min Act: -0.0000

Data Index: 1329449 (The Pile)

Max Activating Token Index: 380

Text #6

Max Range: 0.3403. Min Range: -0.3403

Max Act: 0.2805. Min Act: -0.0000

Data Index: 790220 (The Pile)

Max Activating Token Index: 759

Text #7

Max Range: 0.3403. Min Range: -0.3403

Max Act: 0.2819. Min Act: -0.0000

Data Index: 508674 (The Pile)

Max Activating Token Index: 789

Text #8

Max Range: 0.3403. Min Range: -0.3403

Max Act: 0.2656. Min Act: -0.0000

Data Index: 1590475 (The Pile)

Max Activating Token Index: 16

Text #9

Max Range: 0.3403. Min Range: -0.3403

Max Act: 0.2666. Min Act: -0.0000

Data Index: 559347 (The Pile)

Max Activating Token Index: 881

Text #10

Max Range: 0.3403. Min Range: -0.3403

Max Act: 0.2722. Min Act: -0.0000

Data Index: 715003 (The Pile)

Max Activating Token Index: 414

Text #11

Max Range: 0.3403. Min Range: -0.3403

Max Act: 0.2482. Min Act: -0.0000

Data Index: 1201021 (The Pile)

Max Activating Token Index: 222

Text #12

Max Range: 0.3403. Min Range: -0.3403

Max Act: 0.2597. Min Act: -0.0000

Data Index: 1067261 (The Pile)

Max Activating Token Index: 511

Text #13

Max Range: 0.3403. Min Range: -0.3403

Max Act: 0.2653. Min Act: -0.0000

Data Index: 469944 (The Pile)

Max Activating Token Index: 200

Text #14

Max Range: 0.3403. Min Range: -0.3403

Max Act: 0.2639. Min Act: -0.0000

Data Index: 125406 (The Pile)

Max Activating Token Index: 1011

Text #15

Max Range: 0.3403. Min Range: -0.3403

Max Act: 0.2421. Min Act: -0.0000

Data Index: 1434382 (The Pile)

Max Activating Token Index: 890

Text #16

Max Range: 0.3403. Min Range: -0.3403

Max Act: 0.2480. Min Act: -0.0000

Data Index: 1822520 (The Pile)

Max Activating Token Index: 105

Text #17

Max Range: 0.3403. Min Range: -0.3403

Max Act: 0.2514. Min Act: -0.0000

Data Index: 947043 (The Pile)

Max Activating Token Index: 870

Text #18

Max Range: 0.3403. Min Range: -0.3403

Max Act: 0.2500. Min Act: -0.0000

Data Index: 638602 (The Pile)

Max Activating Token Index: 714

Text #19

Max Range: 0.3403. Min Range: -0.3403

Max Act: 0.2498. Min Act: -0.0000

Data Index: 1676484 (The Pile)

Max Activating Token Index: 62