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

Dataset: The Pile

Neuron 3296 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9534. Min Range: -0.9534

Max Act: 0.8655. Min Act: -0.0000

Data Index: 507745 (The Pile)

Max Activating Token Index: 914

Text #1

Max Range: 0.9534. Min Range: -0.9534

Max Act: 0.9454. Min Act: -0.0000

Data Index: 27315 (The Pile)

Max Activating Token Index: 476

Text #2

Max Range: 0.9534. Min Range: -0.9534

Max Act: 0.9119. Min Act: -0.0000

Data Index: 1768172 (The Pile)

Max Activating Token Index: 432

Text #3

Max Range: 0.9534. Min Range: -0.9534

Max Act: 0.9534. Min Act: -0.0000

Data Index: 435999 (The Pile)

Max Activating Token Index: 317

Text #4

Max Range: 0.9534. Min Range: -0.9534

Max Act: 0.8453. Min Act: -0.0000

Data Index: 608154 (The Pile)

Max Activating Token Index: 570

Text #5

Max Range: 0.9534. Min Range: -0.9534

Max Act: 0.8731. Min Act: -0.0000

Data Index: 1979919 (The Pile)

Max Activating Token Index: 451

Text #6

Max Range: 0.9534. Min Range: -0.9534

Max Act: 0.8879. Min Act: -0.0000

Data Index: 1701214 (The Pile)

Max Activating Token Index: 790

Text #7

Max Range: 0.9534. Min Range: -0.9534

Max Act: 0.8633. Min Act: -0.0000

Data Index: 275355 (The Pile)

Max Activating Token Index: 585

Text #8

Max Range: 0.9534. Min Range: -0.9534

Max Act: 0.8109. Min Act: -0.0000

Data Index: 1542174 (The Pile)

Max Activating Token Index: 798

Text #9

Max Range: 0.9534. Min Range: -0.9534

Max Act: 0.7599. Min Act: -0.0000

Data Index: 1233031 (The Pile)

Max Activating Token Index: 71

Text #10

Max Range: 0.9534. Min Range: -0.9534

Max Act: 0.8017. Min Act: -0.0000

Data Index: 56179 (The Pile)

Max Activating Token Index: 434

Text #11

Max Range: 0.9534. Min Range: -0.9534

Max Act: 0.8377. Min Act: -0.0000

Data Index: 342949 (The Pile)

Max Activating Token Index: 915

Text #12

Max Range: 0.9534. Min Range: -0.9534

Max Act: 0.7786. Min Act: -0.0000

Data Index: 1935866 (The Pile)

Max Activating Token Index: 716

Text #13

Max Range: 0.9534. Min Range: -0.9534

Max Act: 0.7546. Min Act: -0.0000

Data Index: 458911 (The Pile)

Max Activating Token Index: 509

Text #14

Max Range: 0.9534. Min Range: -0.9534

Max Act: 0.7560. Min Act: -0.0000

Data Index: 1680304 (The Pile)

Max Activating Token Index: 386

Text #15

Max Range: 0.9534. Min Range: -0.9534

Max Act: 0.8262. Min Act: -0.0000

Data Index: 357980 (The Pile)

Max Activating Token Index: 579

Text #16

Max Range: 0.9534. Min Range: -0.9534

Max Act: 0.8211. Min Act: -0.0000

Data Index: 1874662 (The Pile)

Max Activating Token Index: 33

Text #17

Max Range: 0.9534. Min Range: -0.9534

Max Act: 0.7182. Min Act: -0.0000

Data Index: 179709 (The Pile)

Max Activating Token Index: 444

Text #18

Max Range: 0.9534. Min Range: -0.9534

Max Act: 0.7638. Min Act: -0.0000

Data Index: 77622 (The Pile)

Max Activating Token Index: 970

Text #19

Max Range: 0.9534. Min Range: -0.9534

Max Act: 0.7803. Min Act: -0.0000

Data Index: 1234817 (The Pile)

Max Activating Token Index: 428