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

Dataset: The Pile

Neuron 3362 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: 0.3215. Min Range: -0.3215

Max Act: 0.3215. Min Act: -0.0000

Data Index: 929153 (The Pile)

Max Activating Token Index: 66

Text #1

Max Range: 0.3215. Min Range: -0.3215

Max Act: 0.2886. Min Act: -0.0000

Data Index: 1032921 (The Pile)

Max Activating Token Index: 1018

Text #2

Max Range: 0.3215. Min Range: -0.3215

Max Act: 0.2967. Min Act: -0.0000

Data Index: 523716 (The Pile)

Max Activating Token Index: 601

Text #3

Max Range: 0.3215. Min Range: -0.3215

Max Act: 0.2894. Min Act: -0.0000

Data Index: 838073 (The Pile)

Max Activating Token Index: 354

Text #4

Max Range: 0.3215. Min Range: -0.3215

Max Act: 0.2633. Min Act: -0.0000

Data Index: 379980 (The Pile)

Max Activating Token Index: 918

Text #5

Max Range: 0.3215. Min Range: -0.3215

Max Act: 0.2422. Min Act: -0.0000

Data Index: 1243634 (The Pile)

Max Activating Token Index: 30

Text #6

Max Range: 0.3215. Min Range: -0.3215

Max Act: 0.2427. Min Act: -0.0000

Data Index: 1521150 (The Pile)

Max Activating Token Index: 643

Text #7

Max Range: 0.3215. Min Range: -0.3215

Max Act: 0.2423. Min Act: -0.0000

Data Index: 1462631 (The Pile)

Max Activating Token Index: 587

Text #8

Max Range: 0.3215. Min Range: -0.3215

Max Act: 0.2339. Min Act: -0.0000

Data Index: 1519786 (The Pile)

Max Activating Token Index: 1022

Text #9

Max Range: 0.3215. Min Range: -0.3215

Max Act: 0.2512. Min Act: -0.0000

Data Index: 1578542 (The Pile)

Max Activating Token Index: 670

Text #10

Max Range: 0.3215. Min Range: -0.3215

Max Act: 0.2479. Min Act: -0.0000

Data Index: 1134090 (The Pile)

Max Activating Token Index: 875

Text #11

Max Range: 0.3215. Min Range: -0.3215

Max Act: 0.2425. Min Act: -0.0000

Data Index: 1092379 (The Pile)

Max Activating Token Index: 305

Text #12

Max Range: 0.3215. Min Range: -0.3215

Max Act: 0.2238. Min Act: -0.0000

Data Index: 1544986 (The Pile)

Max Activating Token Index: 889

Text #13

Max Range: 0.3215. Min Range: -0.3215

Max Act: 0.2333. Min Act: -0.0000

Data Index: 1845002 (The Pile)

Max Activating Token Index: 341

Text #14

Max Range: 0.3215. Min Range: -0.3215

Max Act: 0.2088. Min Act: -0.0000

Data Index: 1790738 (The Pile)

Max Activating Token Index: 955

Text #15

Max Range: 0.3215. Min Range: -0.3215

Max Act: 0.2333. Min Act: -0.0000

Data Index: 1372393 (The Pile)

Max Activating Token Index: 839

Text #16

Max Range: 0.3215. Min Range: -0.3215

Max Act: 0.2334. Min Act: -0.0000

Data Index: 1845726 (The Pile)

Max Activating Token Index: 395

Text #17

Max Range: 0.3215. Min Range: -0.3215

Max Act: 0.2421. Min Act: -0.0000

Data Index: 1539012 (The Pile)

Max Activating Token Index: 552

Text #18

Max Range: 0.3215. Min Range: -0.3215

Max Act: 0.2255. Min Act: -0.0000

Data Index: 1361121 (The Pile)

Max Activating Token Index: 954

Text #19

Max Range: 0.3215. Min Range: -0.3215

Max Act: 0.2327. Min Act: -0.0000

Data Index: 1106373 (The Pile)

Max Activating Token Index: 173