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

Dataset: The Pile

Neuron 2318 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9613. Min Range: -3.9613

Max Act: 3.5673. Min Act: -0.0000

Data Index: 1857392 (The Pile)

Max Activating Token Index: 720

Text #1

Max Range: 3.9613. Min Range: -3.9613

Max Act: 3.6649. Min Act: -0.0000

Data Index: 487984 (The Pile)

Max Activating Token Index: 623

Text #2

Max Range: 3.9613. Min Range: -3.9613

Max Act: 3.9613. Min Act: -0.0000

Data Index: 937154 (The Pile)

Max Activating Token Index: 951

Text #3

Max Range: 3.9613. Min Range: -3.9613

Max Act: 3.5345. Min Act: -0.0000

Data Index: 327505 (The Pile)

Max Activating Token Index: 781

Text #4

Max Range: 3.9613. Min Range: -3.9613

Max Act: 3.3331. Min Act: -0.0000

Data Index: 717906 (The Pile)

Max Activating Token Index: 860

Text #5

Max Range: 3.9613. Min Range: -3.9613

Max Act: 3.1545. Min Act: -0.0000

Data Index: 1936259 (The Pile)

Max Activating Token Index: 482

Text #6

Max Range: 3.9613. Min Range: -3.9613

Max Act: 3.2045. Min Act: -0.0000

Data Index: 844643 (The Pile)

Max Activating Token Index: 477

Text #7

Max Range: 3.9613. Min Range: -3.9613

Max Act: 3.2113. Min Act: -0.0000

Data Index: 956278 (The Pile)

Max Activating Token Index: 635

Text #8

Max Range: 3.9613. Min Range: -3.9613

Max Act: 3.2016. Min Act: -0.0000

Data Index: 1679046 (The Pile)

Max Activating Token Index: 360

Text #9

Max Range: 3.9613. Min Range: -3.9613

Max Act: 2.9652. Min Act: -0.0000

Data Index: 826687 (The Pile)

Max Activating Token Index: 138

Text #10

Max Range: 3.9613. Min Range: -3.9613

Max Act: 3.0858. Min Act: -0.0000

Data Index: 1294414 (The Pile)

Max Activating Token Index: 106

Text #11

Max Range: 3.9613. Min Range: -3.9613

Max Act: 3.0487. Min Act: -0.0000

Data Index: 1828023 (The Pile)

Max Activating Token Index: 191

Text #12

Max Range: 3.9613. Min Range: -3.9613

Max Act: 3.1728. Min Act: -0.0000

Data Index: 1663898 (The Pile)

Max Activating Token Index: 887

Text #13

Max Range: 3.9613. Min Range: -3.9613

Max Act: 2.8973. Min Act: -0.0000

Data Index: 1929171 (The Pile)

Max Activating Token Index: 514

Text #14

Max Range: 3.9613. Min Range: -3.9613

Max Act: 2.8643. Min Act: -0.0000

Data Index: 1051290 (The Pile)

Max Activating Token Index: 155

Text #15

Max Range: 3.9613. Min Range: -3.9613

Max Act: 3.1345. Min Act: -0.0000

Data Index: 615092 (The Pile)

Max Activating Token Index: 115

Text #16

Max Range: 3.9613. Min Range: -3.9613

Max Act: 3.1357. Min Act: -0.0000

Data Index: 79728 (The Pile)

Max Activating Token Index: 984

Text #17

Max Range: 3.9613. Min Range: -3.9613

Max Act: 2.9726. Min Act: -0.0000

Data Index: 414329 (The Pile)

Max Activating Token Index: 126

Text #18

Max Range: 3.9613. Min Range: -3.9613

Max Act: 2.8117. Min Act: -0.0000

Data Index: 889734 (The Pile)

Max Activating Token Index: 386

Text #19

Max Range: 3.9613. Min Range: -3.9613

Max Act: 2.9424. Min Act: -0.0000

Data Index: 1961010 (The Pile)

Max Activating Token Index: 271