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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3044 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0666. Min Act: -0.0003

Data Index: 110674 (C4 (Web Text))

Max Activating Token Index: 643

Text #1

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0630. Min Act: -0.0002

Data Index: 861790 (C4 (Web Text))

Max Activating Token Index: 788

Text #2

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0674. Min Act: -0.0003

Data Index: 107550 (C4 (Web Text))

Max Activating Token Index: 1008

Text #3

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0610. Min Act: -0.0002

Data Index: 660425 (C4 (Web Text))

Max Activating Token Index: 223

Text #4

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0571. Min Act: -0.0003

Data Index: 92202 (C4 (Web Text))

Max Activating Token Index: 929

Text #5

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0573. Min Act: -0.0003

Data Index: 369877 (C4 (Web Text))

Max Activating Token Index: 558

Text #6

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0574. Min Act: -0.0003

Data Index: 1112970 (C4 (Web Text))

Max Activating Token Index: 260

Text #7

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0567. Min Act: -0.0003

Data Index: 1183707 (C4 (Web Text))

Max Activating Token Index: 298

Text #8

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0552. Min Act: -0.0003

Data Index: 733854 (C4 (Web Text))

Max Activating Token Index: 462

Text #9

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0556. Min Act: -0.0003

Data Index: 656300 (C4 (Web Text))

Max Activating Token Index: 1018

Text #10

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0534. Min Act: -0.0003

Data Index: 633824 (C4 (Web Text))

Max Activating Token Index: 490

Text #11

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0542. Min Act: -0.0003

Data Index: 223875 (C4 (Web Text))

Max Activating Token Index: 672

Text #12

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0519. Min Act: -0.0002

Data Index: 255707 (C4 (Web Text))

Max Activating Token Index: 352

Text #13

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0546. Min Act: -0.0003

Data Index: 762268 (C4 (Web Text))

Max Activating Token Index: 729

Text #14

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0527. Min Act: -0.0003

Data Index: 813623 (C4 (Web Text))

Max Activating Token Index: 425

Text #15

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0537. Min Act: -0.0002

Data Index: 711276 (C4 (Web Text))

Max Activating Token Index: 186

Text #16

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0525. Min Act: -0.0003

Data Index: 18392 (C4 (Web Text))

Max Activating Token Index: 362

Text #17

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0544. Min Act: -0.0003

Data Index: 455983 (C4 (Web Text))

Max Activating Token Index: 226

Text #18

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0525. Min Act: -0.0002

Data Index: 702763 (C4 (Web Text))

Max Activating Token Index: 493

Text #19

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0514. Min Act: -0.0002

Data Index: 539021 (C4 (Web Text))

Max Activating Token Index: 369