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

Dataset: The Pile

Neuron 3445 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2979. Min Range: -0.2979

Max Act: 0.2834. Min Act: -0.0000

Data Index: 1518348 (The Pile)

Max Activating Token Index: 885

Text #1

Max Range: 0.2979. Min Range: -0.2979

Max Act: 0.2979. Min Act: -0.0000

Data Index: 1116932 (The Pile)

Max Activating Token Index: 221

Text #2

Max Range: 0.2979. Min Range: -0.2979

Max Act: 0.2779. Min Act: -0.0000

Data Index: 961387 (The Pile)

Max Activating Token Index: 991

Text #3

Max Range: 0.2979. Min Range: -0.2979

Max Act: 0.2603. Min Act: -0.0000

Data Index: 115633 (The Pile)

Max Activating Token Index: 803

Text #4

Max Range: 0.2979. Min Range: -0.2979

Max Act: 0.2368. Min Act: -0.0000

Data Index: 74845 (The Pile)

Max Activating Token Index: 983

Text #5

Max Range: 0.2979. Min Range: -0.2979

Max Act: 0.2818. Min Act: -0.0000

Data Index: 1509904 (The Pile)

Max Activating Token Index: 635

Text #6

Max Range: 0.2979. Min Range: -0.2979

Max Act: 0.2400. Min Act: -0.0000

Data Index: 1182762 (The Pile)

Max Activating Token Index: 894

Text #7

Max Range: 0.2979. Min Range: -0.2979

Max Act: 0.2623. Min Act: -0.0000

Data Index: 35557 (The Pile)

Max Activating Token Index: 932

Text #8

Max Range: 0.2979. Min Range: -0.2979

Max Act: 0.2605. Min Act: -0.0000

Data Index: 1922787 (The Pile)

Max Activating Token Index: 472

Text #9

Max Range: 0.2979. Min Range: -0.2979

Max Act: 0.2788. Min Act: -0.0000

Data Index: 1715410 (The Pile)

Max Activating Token Index: 632

Text #10

Max Range: 0.2979. Min Range: -0.2979

Max Act: 0.2941. Min Act: -0.0000

Data Index: 1055389 (The Pile)

Max Activating Token Index: 681

Text #11

Max Range: 0.2979. Min Range: -0.2979

Max Act: 0.2033. Min Act: -0.0000

Data Index: 860161 (The Pile)

Max Activating Token Index: 220

Text #12

Max Range: 0.2979. Min Range: -0.2979

Max Act: 0.2473. Min Act: -0.0000

Data Index: 1296782 (The Pile)

Max Activating Token Index: 818

Text #13

Max Range: 0.2979. Min Range: -0.2979

Max Act: 0.2539. Min Act: -0.0000

Data Index: 32883 (The Pile)

Max Activating Token Index: 168

Text #14

Max Range: 0.2979. Min Range: -0.2979

Max Act: 0.2731. Min Act: -0.0000

Data Index: 808032 (The Pile)

Max Activating Token Index: 370

Text #15

Max Range: 0.2979. Min Range: -0.2979

Max Act: 0.2514. Min Act: -0.0000

Data Index: 1736291 (The Pile)

Max Activating Token Index: 932

Text #16

Max Range: 0.2979. Min Range: -0.2979

Max Act: 0.2579. Min Act: -0.0000

Data Index: 1076810 (The Pile)

Max Activating Token Index: 127

Text #17

Max Range: 0.2979. Min Range: -0.2979

Max Act: 0.2485. Min Act: -0.0000

Data Index: 1314952 (The Pile)

Max Activating Token Index: 219

Text #18

Max Range: 0.2979. Min Range: -0.2979

Max Act: 0.2236. Min Act: -0.0000

Data Index: 1833242 (The Pile)

Max Activating Token Index: 659

Text #19

Max Range: 0.2979. Min Range: -0.2979

Max Act: 0.2440. Min Act: -0.0000

Data Index: 237566 (The Pile)

Max Activating Token Index: 372