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

Dataset: The Pile

Neuron 3952 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3380. Min Range: -1.3380

Max Act: 1.2606. Min Act: -0.0000

Data Index: 1629359 (The Pile)

Max Activating Token Index: 757

Text #1

Max Range: 1.3380. Min Range: -1.3380

Max Act: 1.2600. Min Act: -0.0000

Data Index: 1864739 (The Pile)

Max Activating Token Index: 190

Text #2

Max Range: 1.3380. Min Range: -1.3380

Max Act: 1.3380. Min Act: -0.0000

Data Index: 1616577 (The Pile)

Max Activating Token Index: 193

Text #3

Max Range: 1.3380. Min Range: -1.3380

Max Act: 1.0141. Min Act: -0.0000

Data Index: 353746 (The Pile)

Max Activating Token Index: 739

Text #4

Max Range: 1.3380. Min Range: -1.3380

Max Act: 1.2630. Min Act: -0.0000

Data Index: 14338 (The Pile)

Max Activating Token Index: 619

Text #5

Max Range: 1.3380. Min Range: -1.3380

Max Act: 1.1042. Min Act: 0.0001

Data Index: 1967109 (The Pile)

Max Activating Token Index: 86

Text #6

Max Range: 1.3380. Min Range: -1.3380

Max Act: 1.0820. Min Act: -0.0000

Data Index: 1035378 (The Pile)

Max Activating Token Index: 668

Text #7

Max Range: 1.3380. Min Range: -1.3380

Max Act: 1.0574. Min Act: -0.0000

Data Index: 947330 (The Pile)

Max Activating Token Index: 299

Text #8

Max Range: 1.3380. Min Range: -1.3380

Max Act: 0.9245. Min Act: -0.0000

Data Index: 1097363 (The Pile)

Max Activating Token Index: 875

Text #9

Max Range: 1.3380. Min Range: -1.3380

Max Act: 0.9873. Min Act: -0.0000

Data Index: 1178982 (The Pile)

Max Activating Token Index: 929

Text #10

Max Range: 1.3380. Min Range: -1.3380

Max Act: 0.9140. Min Act: -0.0000

Data Index: 1689887 (The Pile)

Max Activating Token Index: 458

Text #11

Max Range: 1.3380. Min Range: -1.3380

Max Act: 1.0428. Min Act: -0.0000

Data Index: 983366 (The Pile)

Max Activating Token Index: 277

Text #12

Max Range: 1.3380. Min Range: -1.3380

Max Act: 0.8976. Min Act: -0.0000

Data Index: 1276532 (The Pile)

Max Activating Token Index: 689

Text #13

Max Range: 1.3380. Min Range: -1.3380

Max Act: 1.0145. Min Act: -0.0000

Data Index: 320677 (The Pile)

Max Activating Token Index: 523

Text #14

Max Range: 1.3380. Min Range: -1.3380

Max Act: 0.8348. Min Act: -0.0000

Data Index: 535560 (The Pile)

Max Activating Token Index: 568

Text #15

Max Range: 1.3380. Min Range: -1.3380

Max Act: 0.7375. Min Act: 0.0000

Data Index: 1177892 (The Pile)

Max Activating Token Index: 1008

Text #16

Max Range: 1.3380. Min Range: -1.3380

Max Act: 0.7426. Min Act: -0.0000

Data Index: 1834667 (The Pile)

Max Activating Token Index: 970

Text #17

Max Range: 1.3380. Min Range: -1.3380

Max Act: 0.7792. Min Act: -0.0000

Data Index: 391665 (The Pile)

Max Activating Token Index: 720

Text #18

Max Range: 1.3380. Min Range: -1.3380

Max Act: 0.7388. Min Act: -0.0000

Data Index: 1693460 (The Pile)

Max Activating Token Index: 619

Text #19

Max Range: 1.3380. Min Range: -1.3380

Max Act: 0.6400. Min Act: -0.0000

Data Index: 106647 (The Pile)

Max Activating Token Index: 690