Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 2678 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.3306. Min Range: -0.3306

Max Act: 0.3306. Min Act: -0.0001

Data Index: 1221834 (The Pile)

Max Activating Token Index: 672

Text #1

Max Range: 0.3306. Min Range: -0.3306

Max Act: 0.3114. Min Act: -0.0000

Data Index: 1748966 (The Pile)

Max Activating Token Index: 645

Text #2

Max Range: 0.3306. Min Range: -0.3306

Max Act: 0.3156. Min Act: -0.0000

Data Index: 1607433 (The Pile)

Max Activating Token Index: 622

Text #3

Max Range: 0.3306. Min Range: -0.3306

Max Act: 0.2853. Min Act: -0.0001

Data Index: 1760177 (The Pile)

Max Activating Token Index: 729

Text #4

Max Range: 0.3306. Min Range: -0.3306

Max Act: 0.2910. Min Act: -0.0000

Data Index: 582386 (The Pile)

Max Activating Token Index: 238

Text #5

Max Range: 0.3306. Min Range: -0.3306

Max Act: 0.2845. Min Act: -0.0000

Data Index: 1577196 (The Pile)

Max Activating Token Index: 712

Text #6

Max Range: 0.3306. Min Range: -0.3306

Max Act: 0.2833. Min Act: -0.0001

Data Index: 359194 (The Pile)

Max Activating Token Index: 700

Text #7

Max Range: 0.3306. Min Range: -0.3306

Max Act: 0.2827. Min Act: -0.0000

Data Index: 1531681 (The Pile)

Max Activating Token Index: 704

Text #8

Max Range: 0.3306. Min Range: -0.3306

Max Act: 0.3149. Min Act: -0.0001

Data Index: 992810 (The Pile)

Max Activating Token Index: 244

Text #9

Max Range: 0.3306. Min Range: -0.3306

Max Act: 0.2633. Min Act: -0.0001

Data Index: 585060 (The Pile)

Max Activating Token Index: 467

Text #10

Max Range: 0.3306. Min Range: -0.3306

Max Act: 0.2622. Min Act: -0.0000

Data Index: 570854 (The Pile)

Max Activating Token Index: 443

Text #11

Max Range: 0.3306. Min Range: -0.3306

Max Act: 0.2613. Min Act: -0.0000

Data Index: 682346 (The Pile)

Max Activating Token Index: 213

Text #12

Max Range: 0.3306. Min Range: -0.3306

Max Act: 0.2463. Min Act: -0.0000

Data Index: 1826948 (The Pile)

Max Activating Token Index: 369

Text #13

Max Range: 0.3306. Min Range: -0.3306

Max Act: 0.2617. Min Act: -0.0001

Data Index: 288396 (The Pile)

Max Activating Token Index: 529

Text #14

Max Range: 0.3306. Min Range: -0.3306

Max Act: 0.2613. Min Act: -0.0001

Data Index: 1920653 (The Pile)

Max Activating Token Index: 256

Text #15

Max Range: 0.3306. Min Range: -0.3306

Max Act: 0.2462. Min Act: -0.0000

Data Index: 787368 (The Pile)

Max Activating Token Index: 129

Text #16

Max Range: 0.3306. Min Range: -0.3306

Max Act: 0.2537. Min Act: -0.0000

Data Index: 1089922 (The Pile)

Max Activating Token Index: 573

Text #17

Max Range: 0.3306. Min Range: -0.3306

Max Act: 0.2532. Min Act: -0.0000

Data Index: 599973 (The Pile)

Max Activating Token Index: 936

Text #18

Max Range: 0.3306. Min Range: -0.3306

Max Act: 0.2598. Min Act: -0.0001

Data Index: 1333937 (The Pile)

Max Activating Token Index: 155

Text #19

Max Range: 0.3306. Min Range: -0.3306

Max Act: 0.2495. Min Act: -0.0001

Data Index: 1234645 (The Pile)

Max Activating Token Index: 611