Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3216 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.4433. Min Range: -0.4433

Max Act: 0.4433. Min Act: -0.0000

Data Index: 946933 (The Pile)

Max Activating Token Index: 964

Text #1

Max Range: 0.4433. Min Range: -0.4433

Max Act: 0.4363. Min Act: -0.0000

Data Index: 435005 (The Pile)

Max Activating Token Index: 315

Text #2

Max Range: 0.4433. Min Range: -0.4433

Max Act: 0.4431. Min Act: -0.0000

Data Index: 1195724 (The Pile)

Max Activating Token Index: 928

Text #3

Max Range: 0.4433. Min Range: -0.4433

Max Act: 0.4160. Min Act: -0.0000

Data Index: 1206276 (The Pile)

Max Activating Token Index: 790

Text #4

Max Range: 0.4433. Min Range: -0.4433

Max Act: 0.3930. Min Act: -0.0000

Data Index: 1063332 (The Pile)

Max Activating Token Index: 564

Text #5

Max Range: 0.4433. Min Range: -0.4433

Max Act: 0.4044. Min Act: -0.0000

Data Index: 1821710 (The Pile)

Max Activating Token Index: 584

Text #6

Max Range: 0.4433. Min Range: -0.4433

Max Act: 0.3813. Min Act: -0.0000

Data Index: 344414 (The Pile)

Max Activating Token Index: 1018

Text #7

Max Range: 0.4433. Min Range: -0.4433

Max Act: 0.3675. Min Act: -0.0000

Data Index: 685680 (The Pile)

Max Activating Token Index: 445

Text #8

Max Range: 0.4433. Min Range: -0.4433

Max Act: 0.3537. Min Act: -0.0000

Data Index: 684146 (The Pile)

Max Activating Token Index: 375

Text #9

Max Range: 0.4433. Min Range: -0.4433

Max Act: 0.3632. Min Act: -0.0000

Data Index: 224797 (The Pile)

Max Activating Token Index: 968

Text #10

Max Range: 0.4433. Min Range: -0.4433

Max Act: 0.3610. Min Act: -0.0000

Data Index: 1785307 (The Pile)

Max Activating Token Index: 333

Text #11

Max Range: 0.4433. Min Range: -0.4433

Max Act: 0.3589. Min Act: -0.0000

Data Index: 580626 (The Pile)

Max Activating Token Index: 23

Text #12

Max Range: 0.4433. Min Range: -0.4433

Max Act: 0.3409. Min Act: -0.0000

Data Index: 260514 (The Pile)

Max Activating Token Index: 60

Text #13

Max Range: 0.4433. Min Range: -0.4433

Max Act: 0.3477. Min Act: -0.0000

Data Index: 1004880 (The Pile)

Max Activating Token Index: 396

Text #14

Max Range: 0.4433. Min Range: -0.4433

Max Act: 0.3487. Min Act: -0.0000

Data Index: 1671679 (The Pile)

Max Activating Token Index: 1010

Text #15

Max Range: 0.4433. Min Range: -0.4433

Max Act: 0.3564. Min Act: -0.0000

Data Index: 863768 (The Pile)

Max Activating Token Index: 775

Text #16

Max Range: 0.4433. Min Range: -0.4433

Max Act: 0.3588. Min Act: -0.0000

Data Index: 754377 (The Pile)

Max Activating Token Index: 716

Text #17

Max Range: 0.4433. Min Range: -0.4433

Max Act: 0.3541. Min Act: -0.0000

Data Index: 1168712 (The Pile)

Max Activating Token Index: 441

Text #18

Max Range: 0.4433. Min Range: -0.4433

Max Act: 0.3301. Min Act: -0.0000

Data Index: 1672564 (The Pile)

Max Activating Token Index: 456

Text #19

Max Range: 0.4433. Min Range: -0.4433

Max Act: 0.3288. Min Act: -0.0000

Data Index: 863705 (The Pile)

Max Activating Token Index: 873