Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1053 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0643. Min Act: -0.0006

Data Index: 741770 (C4 (Web Text))

Max Activating Token Index: 960

Text #1

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0661. Min Act: -0.0006

Data Index: 689514 (C4 (Web Text))

Max Activating Token Index: 767

Text #2

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0568. Min Act: -0.0006

Data Index: 1307710 (C4 (Web Text))

Max Activating Token Index: 301

Text #3

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0545. Min Act: -0.0006

Data Index: 1088263 (C4 (Web Text))

Max Activating Token Index: 651

Text #4

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0565. Min Act: -0.0006

Data Index: 78434 (C4 (Web Text))

Max Activating Token Index: 602

Text #5

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0540. Min Act: -0.0006

Data Index: 826426 (C4 (Web Text))

Max Activating Token Index: 725

Text #6

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0563. Min Act: -0.0006

Data Index: 1250021 (C4 (Web Text))

Max Activating Token Index: 816

Text #7

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0566. Min Act: -0.0006

Data Index: 1118827 (C4 (Web Text))

Max Activating Token Index: 329

Text #8

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0518. Min Act: -0.0006

Data Index: 244262 (C4 (Web Text))

Max Activating Token Index: 1002

Text #9

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0538. Min Act: -0.0006

Data Index: 540871 (C4 (Web Text))

Max Activating Token Index: 391

Text #10

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0496. Min Act: -0.0006

Data Index: 1309286 (C4 (Web Text))

Max Activating Token Index: 522

Text #11

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0524. Min Act: -0.0006

Data Index: 650712 (C4 (Web Text))

Max Activating Token Index: 889

Text #12

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0510. Min Act: -0.0006

Data Index: 767902 (C4 (Web Text))

Max Activating Token Index: 800

Text #13

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0527. Min Act: -0.0006

Data Index: 1033017 (C4 (Web Text))

Max Activating Token Index: 199

Text #14

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0497. Min Act: -0.0006

Data Index: 1191512 (C4 (Web Text))

Max Activating Token Index: 298

Text #15

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0503. Min Act: -0.0006

Data Index: 347349 (C4 (Web Text))

Max Activating Token Index: 133

Text #16

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0502. Min Act: -0.0006

Data Index: 894747 (C4 (Web Text))

Max Activating Token Index: 411

Text #17

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0489. Min Act: -0.0006

Data Index: 135303 (C4 (Web Text))

Max Activating Token Index: 44

Text #18

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0498. Min Act: -0.0006

Data Index: 1347667 (C4 (Web Text))

Max Activating Token Index: 906

Text #19

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0484. Min Act: -0.0006

Data Index: 741588 (C4 (Web Text))

Max Activating Token Index: 738