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

Dataset: The Pile

Neuron 2980 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: 0.3469. Min Range: -0.3469

Max Act: 0.3469. Min Act: 0.0000

Data Index: 1279806 (The Pile)

Max Activating Token Index: 374

Text #1

Max Range: 0.3469. Min Range: -0.3469

Max Act: 0.3260. Min Act: 0.0000

Data Index: 1174567 (The Pile)

Max Activating Token Index: 211

Text #2

Max Range: 0.3469. Min Range: -0.3469

Max Act: 0.3343. Min Act: -0.0000

Data Index: 779402 (The Pile)

Max Activating Token Index: 365

Text #3

Max Range: 0.3469. Min Range: -0.3469

Max Act: 0.2938. Min Act: -0.0000

Data Index: 810919 (The Pile)

Max Activating Token Index: 504

Text #4

Max Range: 0.3469. Min Range: -0.3469

Max Act: 0.2837. Min Act: -0.0000

Data Index: 1829135 (The Pile)

Max Activating Token Index: 966

Text #5

Max Range: 0.3469. Min Range: -0.3469

Max Act: 0.2887. Min Act: -0.0000

Data Index: 623241 (The Pile)

Max Activating Token Index: 262

Text #6

Max Range: 0.3469. Min Range: -0.3469

Max Act: 0.2777. Min Act: 0.0000

Data Index: 159453 (The Pile)

Max Activating Token Index: 337

Text #7

Max Range: 0.3469. Min Range: -0.3469

Max Act: 0.2720. Min Act: -0.0000

Data Index: 754503 (The Pile)

Max Activating Token Index: 774

Text #8

Max Range: 0.3469. Min Range: -0.3469

Max Act: 0.2667. Min Act: -0.0000

Data Index: 118752 (The Pile)

Max Activating Token Index: 744

Text #9

Max Range: 0.3469. Min Range: -0.3469

Max Act: 0.2671. Min Act: -0.0000

Data Index: 1363498 (The Pile)

Max Activating Token Index: 526

Text #10

Max Range: 0.3469. Min Range: -0.3469

Max Act: 0.2757. Min Act: -0.0000

Data Index: 818674 (The Pile)

Max Activating Token Index: 949

Text #11

Max Range: 0.3469. Min Range: -0.3469

Max Act: 0.2665. Min Act: -0.0000

Data Index: 1331973 (The Pile)

Max Activating Token Index: 901

Text #12

Max Range: 0.3469. Min Range: -0.3469

Max Act: 0.2674. Min Act: 0.0000

Data Index: 927345 (The Pile)

Max Activating Token Index: 452

Text #13

Max Range: 0.3469. Min Range: -0.3469

Max Act: 0.2639. Min Act: 0.0000

Data Index: 899850 (The Pile)

Max Activating Token Index: 748

Text #14

Max Range: 0.3469. Min Range: -0.3469

Max Act: 0.2528. Min Act: -0.0000

Data Index: 843056 (The Pile)

Max Activating Token Index: 143

Text #15

Max Range: 0.3469. Min Range: -0.3469

Max Act: 0.2710. Min Act: -0.0000

Data Index: 1600579 (The Pile)

Max Activating Token Index: 252

Text #16

Max Range: 0.3469. Min Range: -0.3469

Max Act: 0.2428. Min Act: -0.0000

Data Index: 182741 (The Pile)

Max Activating Token Index: 72

Text #17

Max Range: 0.3469. Min Range: -0.3469

Max Act: 0.2604. Min Act: -0.0000

Data Index: 732136 (The Pile)

Max Activating Token Index: 1012

Text #18

Max Range: 0.3469. Min Range: -0.3469

Max Act: 0.2608. Min Act: 0.0000

Data Index: 629072 (The Pile)

Max Activating Token Index: 844

Text #19

Max Range: 0.3469. Min Range: -0.3469

Max Act: 0.2578. Min Act: -0.0000

Data Index: 1743144 (The Pile)

Max Activating Token Index: 269