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

Dataset: The Pile

Neuron 2243 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0587. Min Act: -0.0000

Data Index: 841634 (The Pile)

Max Activating Token Index: 275

Text #1

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0577. Min Act: -0.0000

Data Index: 280035 (The Pile)

Max Activating Token Index: 22

Text #2

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0545. Min Act: -0.0001

Data Index: 1531863 (The Pile)

Max Activating Token Index: 47

Text #3

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0531. Min Act: -0.0000

Data Index: 1970177 (The Pile)

Max Activating Token Index: 41

Text #4

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0513. Min Act: 0.0000

Data Index: 1665343 (The Pile)

Max Activating Token Index: 260

Text #5

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0508. Min Act: -0.0000

Data Index: 1923017 (The Pile)

Max Activating Token Index: 412

Text #6

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0486. Min Act: -0.0000

Data Index: 538993 (The Pile)

Max Activating Token Index: 218

Text #7

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0502. Min Act: -0.0000

Data Index: 1282210 (The Pile)

Max Activating Token Index: 73

Text #8

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0503. Min Act: -0.0000

Data Index: 1940026 (The Pile)

Max Activating Token Index: 214

Text #9

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0501. Min Act: -0.0000

Data Index: 672893 (The Pile)

Max Activating Token Index: 701

Text #10

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0499. Min Act: -0.0000

Data Index: 1401444 (The Pile)

Max Activating Token Index: 58

Text #11

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0498. Min Act: -0.0000

Data Index: 928453 (The Pile)

Max Activating Token Index: 435

Text #12

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0494. Min Act: -0.0000

Data Index: 378999 (The Pile)

Max Activating Token Index: 708

Text #13

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0491. Min Act: -0.0000

Data Index: 276724 (The Pile)

Max Activating Token Index: 179

Text #14

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0488. Min Act: -0.0000

Data Index: 1829782 (The Pile)

Max Activating Token Index: 343

Text #15

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0486. Min Act: -0.0000

Data Index: 572748 (The Pile)

Max Activating Token Index: 84

Text #16

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0485. Min Act: -0.0000

Data Index: 159118 (The Pile)

Max Activating Token Index: 151

Text #17

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0483. Min Act: -0.0000

Data Index: 399459 (The Pile)

Max Activating Token Index: 1016

Text #18

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0483. Min Act: -0.0000

Data Index: 1368309 (The Pile)

Max Activating Token Index: 694

Text #19

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0481. Min Act: -0.0000

Data Index: 11155 (The Pile)

Max Activating Token Index: 1011