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

Dataset: The Pile

Neuron 1142 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3473. Min Range: -0.3473

Max Act: 0.3473. Min Act: -0.0000

Data Index: 686592 (The Pile)

Max Activating Token Index: 495

Text #1

Max Range: 0.3473. Min Range: -0.3473

Max Act: 0.2551. Min Act: -0.0000

Data Index: 320879 (The Pile)

Max Activating Token Index: 906

Text #2

Max Range: 0.3473. Min Range: -0.3473

Max Act: 0.2565. Min Act: -0.0000

Data Index: 325460 (The Pile)

Max Activating Token Index: 304

Text #3

Max Range: 0.3473. Min Range: -0.3473

Max Act: 0.2745. Min Act: -0.0000

Data Index: 531827 (The Pile)

Max Activating Token Index: 813

Text #4

Max Range: 0.3473. Min Range: -0.3473

Max Act: 0.2518. Min Act: -0.0000

Data Index: 444848 (The Pile)

Max Activating Token Index: 562

Text #5

Max Range: 0.3473. Min Range: -0.3473

Max Act: 0.2018. Min Act: -0.0000

Data Index: 1162420 (The Pile)

Max Activating Token Index: 518

Text #6

Max Range: 0.3473. Min Range: -0.3473

Max Act: 0.2480. Min Act: -0.0000

Data Index: 227101 (The Pile)

Max Activating Token Index: 704

Text #7

Max Range: 0.3473. Min Range: -0.3473

Max Act: 0.2457. Min Act: -0.0000

Data Index: 1728328 (The Pile)

Max Activating Token Index: 656

Text #8

Max Range: 0.3473. Min Range: -0.3473

Max Act: 0.2392. Min Act: -0.0000

Data Index: 373187 (The Pile)

Max Activating Token Index: 715

Text #9

Max Range: 0.3473. Min Range: -0.3473

Max Act: 0.2480. Min Act: -0.0000

Data Index: 1411270 (The Pile)

Max Activating Token Index: 591

Text #10

Max Range: 0.3473. Min Range: -0.3473

Max Act: 0.2615. Min Act: -0.0000

Data Index: 1687734 (The Pile)

Max Activating Token Index: 815

Text #11

Max Range: 0.3473. Min Range: -0.3473

Max Act: 0.2496. Min Act: -0.0000

Data Index: 1351665 (The Pile)

Max Activating Token Index: 580

Text #12

Max Range: 0.3473. Min Range: -0.3473

Max Act: 0.2712. Min Act: -0.0000

Data Index: 954840 (The Pile)

Max Activating Token Index: 503

Text #13

Max Range: 0.3473. Min Range: -0.3473

Max Act: 0.2520. Min Act: -0.0000

Data Index: 675562 (The Pile)

Max Activating Token Index: 513

Text #14

Max Range: 0.3473. Min Range: -0.3473

Max Act: 0.2170. Min Act: -0.0000

Data Index: 66565 (The Pile)

Max Activating Token Index: 903

Text #15

Max Range: 0.3473. Min Range: -0.3473

Max Act: 0.2345. Min Act: -0.0000

Data Index: 962591 (The Pile)

Max Activating Token Index: 850

Text #16

Max Range: 0.3473. Min Range: -0.3473

Max Act: 0.2177. Min Act: -0.0000

Data Index: 1578688 (The Pile)

Max Activating Token Index: 493

Text #17

Max Range: 0.3473. Min Range: -0.3473

Max Act: 0.1776. Min Act: -0.0000

Data Index: 221222 (The Pile)

Max Activating Token Index: 502

Text #18

Max Range: 0.3473. Min Range: -0.3473

Max Act: 0.2083. Min Act: -0.0000

Data Index: 1203668 (The Pile)

Max Activating Token Index: 598

Text #19

Max Range: 0.3473. Min Range: -0.3473

Max Act: 0.1928. Min Act: -0.0000

Data Index: 156898 (The Pile)

Max Activating Token Index: 437