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

Dataset: The Pile

Neuron 2924 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: 0.4784. Min Range: -0.4784

Max Act: 0.4524. Min Act: -0.0000

Data Index: 156774 (The Pile)

Max Activating Token Index: 230

Text #1

Max Range: 0.4784. Min Range: -0.4784

Max Act: 0.4784. Min Act: -0.0000

Data Index: 663358 (The Pile)

Max Activating Token Index: 874

Text #2

Max Range: 0.4784. Min Range: -0.4784

Max Act: 0.4032. Min Act: -0.0000

Data Index: 1201252 (The Pile)

Max Activating Token Index: 592

Text #3

Max Range: 0.4784. Min Range: -0.4784

Max Act: 0.4171. Min Act: -0.0000

Data Index: 1970228 (The Pile)

Max Activating Token Index: 1005

Text #4

Max Range: 0.4784. Min Range: -0.4784

Max Act: 0.4423. Min Act: -0.0000

Data Index: 764569 (The Pile)

Max Activating Token Index: 425

Text #5

Max Range: 0.4784. Min Range: -0.4784

Max Act: 0.3835. Min Act: -0.0000

Data Index: 1614929 (The Pile)

Max Activating Token Index: 729

Text #6

Max Range: 0.4784. Min Range: -0.4784

Max Act: 0.3667. Min Act: -0.0000

Data Index: 10361 (The Pile)

Max Activating Token Index: 441

Text #7

Max Range: 0.4784. Min Range: -0.4784

Max Act: 0.3787. Min Act: -0.0000

Data Index: 1219832 (The Pile)

Max Activating Token Index: 347

Text #8

Max Range: 0.4784. Min Range: -0.4784

Max Act: 0.3800. Min Act: -0.0000

Data Index: 1585175 (The Pile)

Max Activating Token Index: 798

Text #9

Max Range: 0.4784. Min Range: -0.4784

Max Act: 0.3471. Min Act: -0.0000

Data Index: 267882 (The Pile)

Max Activating Token Index: 11

Text #10

Max Range: 0.4784. Min Range: -0.4784

Max Act: 0.3978. Min Act: -0.0000

Data Index: 1688331 (The Pile)

Max Activating Token Index: 984

Text #11

Max Range: 0.4784. Min Range: -0.4784

Max Act: 0.3689. Min Act: -0.0000

Data Index: 253172 (The Pile)

Max Activating Token Index: 84

Text #12

Max Range: 0.4784. Min Range: -0.4784

Max Act: 0.3222. Min Act: -0.0000

Data Index: 540430 (The Pile)

Max Activating Token Index: 63

Text #13

Max Range: 0.4784. Min Range: -0.4784

Max Act: 0.3082. Min Act: -0.0000

Data Index: 1961503 (The Pile)

Max Activating Token Index: 962

Text #14

Max Range: 0.4784. Min Range: -0.4784

Max Act: 0.3688. Min Act: -0.0000

Data Index: 830011 (The Pile)

Max Activating Token Index: 132

Text #15

Max Range: 0.4784. Min Range: -0.4784

Max Act: 0.3580. Min Act: -0.0000

Data Index: 1516408 (The Pile)

Max Activating Token Index: 522

Text #16

Max Range: 0.4784. Min Range: -0.4784

Max Act: 0.3456. Min Act: -0.0000

Data Index: 870023 (The Pile)

Max Activating Token Index: 453

Text #17

Max Range: 0.4784. Min Range: -0.4784

Max Act: 0.2967. Min Act: -0.0000

Data Index: 1542033 (The Pile)

Max Activating Token Index: 120

Text #18

Max Range: 0.4784. Min Range: -0.4784

Max Act: 0.3623. Min Act: -0.0000

Data Index: 1134368 (The Pile)

Max Activating Token Index: 963

Text #19

Max Range: 0.4784. Min Range: -0.4784

Max Act: 0.3647. Min Act: -0.0000

Data Index: 361593 (The Pile)

Max Activating Token Index: 365