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

Dataset: The Pile

Neuron 4464 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3837. Min Range: -0.3837

Max Act: 0.3709. Min Act: -0.0000

Data Index: 722610 (The Pile)

Max Activating Token Index: 872

Text #1

Max Range: 0.3837. Min Range: -0.3837

Max Act: 0.3837. Min Act: -0.0000

Data Index: 1388222 (The Pile)

Max Activating Token Index: 612

Text #2

Max Range: 0.3837. Min Range: -0.3837

Max Act: 0.3570. Min Act: -0.0000

Data Index: 1778492 (The Pile)

Max Activating Token Index: 1004

Text #3

Max Range: 0.3837. Min Range: -0.3837

Max Act: 0.3473. Min Act: -0.0000

Data Index: 129598 (The Pile)

Max Activating Token Index: 693

Text #4

Max Range: 0.3837. Min Range: -0.3837

Max Act: 0.3347. Min Act: -0.0000

Data Index: 259694 (The Pile)

Max Activating Token Index: 263

Text #5

Max Range: 0.3837. Min Range: -0.3837

Max Act: 0.3053. Min Act: -0.0000

Data Index: 248531 (The Pile)

Max Activating Token Index: 440

Text #6

Max Range: 0.3837. Min Range: -0.3837

Max Act: 0.2878. Min Act: -0.0000

Data Index: 16528 (The Pile)

Max Activating Token Index: 223

Text #7

Max Range: 0.3837. Min Range: -0.3837

Max Act: 0.3089. Min Act: -0.0000

Data Index: 67318 (The Pile)

Max Activating Token Index: 735

Text #8

Max Range: 0.3837. Min Range: -0.3837

Max Act: 0.2809. Min Act: -0.0000

Data Index: 1870320 (The Pile)

Max Activating Token Index: 924

Text #9

Max Range: 0.3837. Min Range: -0.3837

Max Act: 0.2600. Min Act: -0.0000

Data Index: 785919 (The Pile)

Max Activating Token Index: 304

Text #10

Max Range: 0.3837. Min Range: -0.3837

Max Act: 0.2687. Min Act: -0.0000

Data Index: 1383022 (The Pile)

Max Activating Token Index: 922

Text #11

Max Range: 0.3837. Min Range: -0.3837

Max Act: 0.2405. Min Act: -0.0000

Data Index: 1974706 (The Pile)

Max Activating Token Index: 486

Text #12

Max Range: 0.3837. Min Range: -0.3837

Max Act: 0.2663. Min Act: -0.0000

Data Index: 615328 (The Pile)

Max Activating Token Index: 460

Text #13

Max Range: 0.3837. Min Range: -0.3837

Max Act: 0.2578. Min Act: -0.0000

Data Index: 653413 (The Pile)

Max Activating Token Index: 297

Text #14

Max Range: 0.3837. Min Range: -0.3837

Max Act: 0.2657. Min Act: -0.0000

Data Index: 47394 (The Pile)

Max Activating Token Index: 88

Text #15

Max Range: 0.3837. Min Range: -0.3837

Max Act: 0.2392. Min Act: -0.0000

Data Index: 560020 (The Pile)

Max Activating Token Index: 845

Text #16

Max Range: 0.3837. Min Range: -0.3837

Max Act: 0.2674. Min Act: -0.0000

Data Index: 1607790 (The Pile)

Max Activating Token Index: 928

Text #17

Max Range: 0.3837. Min Range: -0.3837

Max Act: 0.2778. Min Act: -0.0000

Data Index: 1895901 (The Pile)

Max Activating Token Index: 988

Text #18

Max Range: 0.3837. Min Range: -0.3837

Max Act: 0.2629. Min Act: -0.0000

Data Index: 1839199 (The Pile)

Max Activating Token Index: 657

Text #19

Max Range: 0.3837. Min Range: -0.3837

Max Act: 0.2572. Min Act: -0.0000

Data Index: 1325232 (The Pile)

Max Activating Token Index: 590