Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 4033 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.3517. Min Range: -0.3517

Max Act: 0.3517. Min Act: -0.0000

Data Index: 309263 (The Pile)

Max Activating Token Index: 998

Text #1

Max Range: 0.3517. Min Range: -0.3517

Max Act: 0.3339. Min Act: -0.0000

Data Index: 636074 (The Pile)

Max Activating Token Index: 334

Text #2

Max Range: 0.3517. Min Range: -0.3517

Max Act: 0.2937. Min Act: -0.0000

Data Index: 559143 (The Pile)

Max Activating Token Index: 723

Text #3

Max Range: 0.3517. Min Range: -0.3517

Max Act: 0.3033. Min Act: -0.0000

Data Index: 1098156 (The Pile)

Max Activating Token Index: 418

Text #4

Max Range: 0.3517. Min Range: -0.3517

Max Act: 0.3076. Min Act: -0.0000

Data Index: 252315 (The Pile)

Max Activating Token Index: 966

Text #5

Max Range: 0.3517. Min Range: -0.3517

Max Act: 0.2927. Min Act: -0.0000

Data Index: 1483393 (The Pile)

Max Activating Token Index: 564

Text #6

Max Range: 0.3517. Min Range: -0.3517

Max Act: 0.2623. Min Act: -0.0000

Data Index: 1880837 (The Pile)

Max Activating Token Index: 861

Text #7

Max Range: 0.3517. Min Range: -0.3517

Max Act: 0.2843. Min Act: -0.0000

Data Index: 1979264 (The Pile)

Max Activating Token Index: 47

Text #8

Max Range: 0.3517. Min Range: -0.3517

Max Act: 0.2704. Min Act: -0.0000

Data Index: 629784 (The Pile)

Max Activating Token Index: 413

Text #9

Max Range: 0.3517. Min Range: -0.3517

Max Act: 0.2502. Min Act: -0.0000

Data Index: 1431503 (The Pile)

Max Activating Token Index: 743

Text #10

Max Range: 0.3517. Min Range: -0.3517

Max Act: 0.2645. Min Act: -0.0000

Data Index: 213597 (The Pile)

Max Activating Token Index: 154

Text #11

Max Range: 0.3517. Min Range: -0.3517

Max Act: 0.2438. Min Act: -0.0000

Data Index: 969911 (The Pile)

Max Activating Token Index: 536

Text #12

Max Range: 0.3517. Min Range: -0.3517

Max Act: 0.2488. Min Act: -0.0000

Data Index: 264487 (The Pile)

Max Activating Token Index: 486

Text #13

Max Range: 0.3517. Min Range: -0.3517

Max Act: 0.2665. Min Act: -0.0000

Data Index: 1983621 (The Pile)

Max Activating Token Index: 484

Text #14

Max Range: 0.3517. Min Range: -0.3517

Max Act: 0.2486. Min Act: -0.0000

Data Index: 1329883 (The Pile)

Max Activating Token Index: 142

Text #15

Max Range: 0.3517. Min Range: -0.3517

Max Act: 0.2435. Min Act: -0.0000

Data Index: 1583831 (The Pile)

Max Activating Token Index: 256

Text #16

Max Range: 0.3517. Min Range: -0.3517

Max Act: 0.2423. Min Act: -0.0000

Data Index: 1984786 (The Pile)

Max Activating Token Index: 536

Text #17

Max Range: 0.3517. Min Range: -0.3517

Max Act: 0.2317. Min Act: -0.0000

Data Index: 1549948 (The Pile)

Max Activating Token Index: 708

Text #18

Max Range: 0.3517. Min Range: -0.3517

Max Act: 0.2520. Min Act: -0.0000

Data Index: 1915488 (The Pile)

Max Activating Token Index: 322

Text #19

Max Range: 0.3517. Min Range: -0.3517

Max Act: 0.2482. Min Act: -0.0000

Data Index: 488021 (The Pile)

Max Activating Token Index: 675