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

Dataset: The Pile

Neuron 298 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: 0.5643. Min Range: -0.5643

Max Act: 0.5643. Min Act: -0.0000

Data Index: 616243 (The Pile)

Max Activating Token Index: 595

Text #1

Max Range: 0.5643. Min Range: -0.5643

Max Act: 0.4481. Min Act: -0.0000

Data Index: 885867 (The Pile)

Max Activating Token Index: 365

Text #2

Max Range: 0.5643. Min Range: -0.5643

Max Act: 0.4465. Min Act: -0.0000

Data Index: 1785277 (The Pile)

Max Activating Token Index: 442

Text #3

Max Range: 0.5643. Min Range: -0.5643

Max Act: 0.5352. Min Act: -0.0000

Data Index: 1868563 (The Pile)

Max Activating Token Index: 616

Text #4

Max Range: 0.5643. Min Range: -0.5643

Max Act: 0.4657. Min Act: -0.0000

Data Index: 1938106 (The Pile)

Max Activating Token Index: 718

Text #5

Max Range: 0.5643. Min Range: -0.5643

Max Act: 0.3828. Min Act: -0.0000

Data Index: 1356902 (The Pile)

Max Activating Token Index: 145

Text #6

Max Range: 0.5643. Min Range: -0.5643

Max Act: 0.4517. Min Act: -0.0000

Data Index: 652442 (The Pile)

Max Activating Token Index: 574

Text #7

Max Range: 0.5643. Min Range: -0.5643

Max Act: 0.4085. Min Act: -0.0000

Data Index: 1892282 (The Pile)

Max Activating Token Index: 822

Text #8

Max Range: 0.5643. Min Range: -0.5643

Max Act: 0.4017. Min Act: -0.0000

Data Index: 932923 (The Pile)

Max Activating Token Index: 1013

Text #9

Max Range: 0.5643. Min Range: -0.5643

Max Act: 0.3890. Min Act: -0.0000

Data Index: 496693 (The Pile)

Max Activating Token Index: 969

Text #10

Max Range: 0.5643. Min Range: -0.5643

Max Act: 0.3630. Min Act: -0.0000

Data Index: 244302 (The Pile)

Max Activating Token Index: 837

Text #11

Max Range: 0.5643. Min Range: -0.5643

Max Act: 0.4107. Min Act: -0.0000

Data Index: 1305846 (The Pile)

Max Activating Token Index: 537

Text #12

Max Range: 0.5643. Min Range: -0.5643

Max Act: 0.4327. Min Act: -0.0000

Data Index: 262796 (The Pile)

Max Activating Token Index: 958

Text #13

Max Range: 0.5643. Min Range: -0.5643

Max Act: 0.3718. Min Act: -0.0000

Data Index: 356183 (The Pile)

Max Activating Token Index: 831

Text #14

Max Range: 0.5643. Min Range: -0.5643

Max Act: 0.3958. Min Act: -0.0000

Data Index: 1586014 (The Pile)

Max Activating Token Index: 168

Text #15

Max Range: 0.5643. Min Range: -0.5643

Max Act: 0.3673. Min Act: -0.0000

Data Index: 1763056 (The Pile)

Max Activating Token Index: 92

Text #16

Max Range: 0.5643. Min Range: -0.5643

Max Act: 0.3695. Min Act: -0.0000

Data Index: 1880577 (The Pile)

Max Activating Token Index: 780

Text #17

Max Range: 0.5643. Min Range: -0.5643

Max Act: 0.3946. Min Act: -0.0000

Data Index: 955442 (The Pile)

Max Activating Token Index: 604

Text #18

Max Range: 0.5643. Min Range: -0.5643

Max Act: 0.3707. Min Act: -0.0000

Data Index: 3448 (The Pile)

Max Activating Token Index: 552

Text #19

Max Range: 0.5643. Min Range: -0.5643

Max Act: 0.3412. Min Act: -0.0000

Data Index: 265102 (The Pile)

Max Activating Token Index: 934