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

Dataset: The Pile

Neuron 3685 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6568. Min Range: -1.6568

Max Act: 1.6568. Min Act: -0.0000

Data Index: 127909 (The Pile)

Max Activating Token Index: 844

Text #1

Max Range: 1.6568. Min Range: -1.6568

Max Act: 1.4295. Min Act: -0.0000

Data Index: 1415883 (The Pile)

Max Activating Token Index: 464

Text #2

Max Range: 1.6568. Min Range: -1.6568

Max Act: 1.4133. Min Act: -0.0000

Data Index: 1099672 (The Pile)

Max Activating Token Index: 373

Text #3

Max Range: 1.6568. Min Range: -1.6568

Max Act: 1.4844. Min Act: -0.0000

Data Index: 581035 (The Pile)

Max Activating Token Index: 707

Text #4

Max Range: 1.6568. Min Range: -1.6568

Max Act: 1.3970. Min Act: -0.0000

Data Index: 913354 (The Pile)

Max Activating Token Index: 387

Text #5

Max Range: 1.6568. Min Range: -1.6568

Max Act: 1.3036. Min Act: -0.0000

Data Index: 1317145 (The Pile)

Max Activating Token Index: 270

Text #6

Max Range: 1.6568. Min Range: -1.6568

Max Act: 1.3822. Min Act: -0.0000

Data Index: 93106 (The Pile)

Max Activating Token Index: 160

Text #7

Max Range: 1.6568. Min Range: -1.6568

Max Act: 1.3773. Min Act: -0.0000

Data Index: 1459021 (The Pile)

Max Activating Token Index: 179

Text #8

Max Range: 1.6568. Min Range: -1.6568

Max Act: 1.3569. Min Act: -0.0000

Data Index: 1022592 (The Pile)

Max Activating Token Index: 172

Text #9

Max Range: 1.6568. Min Range: -1.6568

Max Act: 1.3543. Min Act: -0.0000

Data Index: 1054819 (The Pile)

Max Activating Token Index: 423

Text #10

Max Range: 1.6568. Min Range: -1.6568

Max Act: 1.3474. Min Act: -0.0000

Data Index: 16087 (The Pile)

Max Activating Token Index: 404

Text #11

Max Range: 1.6568. Min Range: -1.6568

Max Act: 1.3304. Min Act: -0.0000

Data Index: 317994 (The Pile)

Max Activating Token Index: 401

Text #12

Max Range: 1.6568. Min Range: -1.6568

Max Act: 1.3115. Min Act: -0.0000

Data Index: 261398 (The Pile)

Max Activating Token Index: 361

Text #13

Max Range: 1.6568. Min Range: -1.6568

Max Act: 1.2306. Min Act: -0.0000

Data Index: 1195802 (The Pile)

Max Activating Token Index: 334

Text #14

Max Range: 1.6568. Min Range: -1.6568

Max Act: 1.2307. Min Act: -0.0000

Data Index: 383951 (The Pile)

Max Activating Token Index: 28

Text #15

Max Range: 1.6568. Min Range: -1.6568

Max Act: 1.2351. Min Act: -0.0000

Data Index: 1989028 (The Pile)

Max Activating Token Index: 780

Text #16

Max Range: 1.6568. Min Range: -1.6568

Max Act: 1.2709. Min Act: -0.0000

Data Index: 930017 (The Pile)

Max Activating Token Index: 404

Text #17

Max Range: 1.6568. Min Range: -1.6568

Max Act: 1.3508. Min Act: -0.0000

Data Index: 1332482 (The Pile)

Max Activating Token Index: 233

Text #18

Max Range: 1.6568. Min Range: -1.6568

Max Act: 1.2699. Min Act: -0.0000

Data Index: 1920137 (The Pile)

Max Activating Token Index: 953

Text #19

Max Range: 1.6568. Min Range: -1.6568

Max Act: 1.2677. Min Act: -0.0000

Data Index: 1709846 (The Pile)

Max Activating Token Index: 237