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

Dataset: The Pile

Neuron 124 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: 0.4002. Min Range: -0.4002

Max Act: 0.3959. Min Act: -0.0000

Data Index: 954953 (The Pile)

Max Activating Token Index: 358

Text #1

Max Range: 0.4002. Min Range: -0.4002

Max Act: 0.3984. Min Act: -0.0000

Data Index: 417658 (The Pile)

Max Activating Token Index: 525

Text #2

Max Range: 0.4002. Min Range: -0.4002

Max Act: 0.3694. Min Act: -0.0000

Data Index: 1854858 (The Pile)

Max Activating Token Index: 404

Text #3

Max Range: 0.4002. Min Range: -0.4002

Max Act: 0.4002. Min Act: -0.0000

Data Index: 606198 (The Pile)

Max Activating Token Index: 918

Text #4

Max Range: 0.4002. Min Range: -0.4002

Max Act: 0.3502. Min Act: -0.0000

Data Index: 1229280 (The Pile)

Max Activating Token Index: 811

Text #5

Max Range: 0.4002. Min Range: -0.4002

Max Act: 0.3383. Min Act: -0.0000

Data Index: 1747362 (The Pile)

Max Activating Token Index: 491

Text #6

Max Range: 0.4002. Min Range: -0.4002

Max Act: 0.3311. Min Act: -0.0000

Data Index: 520071 (The Pile)

Max Activating Token Index: 716

Text #7

Max Range: 0.4002. Min Range: -0.4002

Max Act: 0.3360. Min Act: -0.0000

Data Index: 1660713 (The Pile)

Max Activating Token Index: 668

Text #8

Max Range: 0.4002. Min Range: -0.4002

Max Act: 0.3169. Min Act: -0.0000

Data Index: 276003 (The Pile)

Max Activating Token Index: 574

Text #9

Max Range: 0.4002. Min Range: -0.4002

Max Act: 0.2815. Min Act: -0.0000

Data Index: 1666362 (The Pile)

Max Activating Token Index: 575

Text #10

Max Range: 0.4002. Min Range: -0.4002

Max Act: 0.2560. Min Act: -0.0000

Data Index: 1392382 (The Pile)

Max Activating Token Index: 827

Text #11

Max Range: 0.4002. Min Range: -0.4002

Max Act: 0.2897. Min Act: -0.0000

Data Index: 1780717 (The Pile)

Max Activating Token Index: 25

Text #12

Max Range: 0.4002. Min Range: -0.4002

Max Act: 0.2731. Min Act: -0.0000

Data Index: 709411 (The Pile)

Max Activating Token Index: 95

Text #13

Max Range: 0.4002. Min Range: -0.4002

Max Act: 0.2691. Min Act: -0.0000

Data Index: 638618 (The Pile)

Max Activating Token Index: 844

Text #14

Max Range: 0.4002. Min Range: -0.4002

Max Act: 0.2901. Min Act: -0.0000

Data Index: 1314582 (The Pile)

Max Activating Token Index: 709

Text #15

Max Range: 0.4002. Min Range: -0.4002

Max Act: 0.2433. Min Act: -0.0000

Data Index: 501760 (The Pile)

Max Activating Token Index: 523

Text #16

Max Range: 0.4002. Min Range: -0.4002

Max Act: 0.2680. Min Act: -0.0000

Data Index: 1487097 (The Pile)

Max Activating Token Index: 826

Text #17

Max Range: 0.4002. Min Range: -0.4002

Max Act: 0.2630. Min Act: -0.0000

Data Index: 1080170 (The Pile)

Max Activating Token Index: 803

Text #18

Max Range: 0.4002. Min Range: -0.4002

Max Act: 0.2816. Min Act: -0.0000

Data Index: 759190 (The Pile)

Max Activating Token Index: 491

Text #19

Max Range: 0.4002. Min Range: -0.4002

Max Act: 0.2603. Min Act: -0.0000

Data Index: 1003113 (The Pile)

Max Activating Token Index: 814