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

Dataset: The Pile

Neuron 1494 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: 0.4659. Min Range: -0.4659

Max Act: 0.4659. Min Act: -0.0000

Data Index: 1491002 (The Pile)

Max Activating Token Index: 148

Text #1

Max Range: 0.4659. Min Range: -0.4659

Max Act: 0.3610. Min Act: -0.0000

Data Index: 663519 (The Pile)

Max Activating Token Index: 281

Text #2

Max Range: 0.4659. Min Range: -0.4659

Max Act: 0.3499. Min Act: -0.0000

Data Index: 596844 (The Pile)

Max Activating Token Index: 155

Text #3

Max Range: 0.4659. Min Range: -0.4659

Max Act: 0.3394. Min Act: -0.0000

Data Index: 1010597 (The Pile)

Max Activating Token Index: 174

Text #4

Max Range: 0.4659. Min Range: -0.4659

Max Act: 0.3364. Min Act: -0.0000

Data Index: 620812 (The Pile)

Max Activating Token Index: 39

Text #5

Max Range: 0.4659. Min Range: -0.4659

Max Act: 0.3171. Min Act: -0.0000

Data Index: 1654188 (The Pile)

Max Activating Token Index: 535

Text #6

Max Range: 0.4659. Min Range: -0.4659

Max Act: 0.3099. Min Act: -0.0000

Data Index: 1574568 (The Pile)

Max Activating Token Index: 135

Text #7

Max Range: 0.4659. Min Range: -0.4659

Max Act: 0.3124. Min Act: -0.0000

Data Index: 26284 (The Pile)

Max Activating Token Index: 326

Text #8

Max Range: 0.4659. Min Range: -0.4659

Max Act: 0.3117. Min Act: -0.0000

Data Index: 780860 (The Pile)

Max Activating Token Index: 40

Text #9

Max Range: 0.4659. Min Range: -0.4659

Max Act: 0.3157. Min Act: -0.0000

Data Index: 1604113 (The Pile)

Max Activating Token Index: 84

Text #10

Max Range: 0.4659. Min Range: -0.4659

Max Act: 0.3059. Min Act: -0.0000

Data Index: 629504 (The Pile)

Max Activating Token Index: 850

Text #11

Max Range: 0.4659. Min Range: -0.4659

Max Act: 0.2933. Min Act: -0.0000

Data Index: 1895261 (The Pile)

Max Activating Token Index: 614

Text #12

Max Range: 0.4659. Min Range: -0.4659

Max Act: 0.3000. Min Act: -0.0000

Data Index: 1310850 (The Pile)

Max Activating Token Index: 92

Text #13

Max Range: 0.4659. Min Range: -0.4659

Max Act: 0.2972. Min Act: -0.0000

Data Index: 1038387 (The Pile)

Max Activating Token Index: 548

Text #14

Max Range: 0.4659. Min Range: -0.4659

Max Act: 0.2876. Min Act: -0.0000

Data Index: 1959289 (The Pile)

Max Activating Token Index: 987

Text #15

Max Range: 0.4659. Min Range: -0.4659

Max Act: 0.2853. Min Act: -0.0000

Data Index: 511051 (The Pile)

Max Activating Token Index: 749

Text #16

Max Range: 0.4659. Min Range: -0.4659

Max Act: 0.2851. Min Act: -0.0000

Data Index: 470278 (The Pile)

Max Activating Token Index: 100

Text #17

Max Range: 0.4659. Min Range: -0.4659

Max Act: 0.2835. Min Act: -0.0000

Data Index: 1084425 (The Pile)

Max Activating Token Index: 531

Text #18

Max Range: 0.4659. Min Range: -0.4659

Max Act: 0.2915. Min Act: -0.0000

Data Index: 426664 (The Pile)

Max Activating Token Index: 488

Text #19

Max Range: 0.4659. Min Range: -0.4659

Max Act: 0.2879. Min Act: -0.0000

Data Index: 945760 (The Pile)

Max Activating Token Index: 682