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

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

Neuron 986 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0591. Min Act: -0.0003

Data Index: 1617224 (Python Code)

Max Activating Token Index: 802

Text #1

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0532. Min Act: -0.0003

Data Index: 665135 (C4 (Web Text))

Max Activating Token Index: 482

Text #2

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0542. Min Act: -0.0003

Data Index: 1357279 (C4 (Web Text))

Max Activating Token Index: 500

Text #3

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0529. Min Act: -0.0003

Data Index: 340613 (C4 (Web Text))

Max Activating Token Index: 872

Text #4

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0493. Min Act: -0.0003

Data Index: 921726 (C4 (Web Text))

Max Activating Token Index: 559

Text #5

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0505. Min Act: -0.0003

Data Index: 1599781 (Python Code)

Max Activating Token Index: 97

Text #6

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0481. Min Act: -0.0003

Data Index: 722328 (C4 (Web Text))

Max Activating Token Index: 891

Text #7

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0483. Min Act: -0.0003

Data Index: 276499 (C4 (Web Text))

Max Activating Token Index: 168

Text #8

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0448. Min Act: -0.0003

Data Index: 1058186 (C4 (Web Text))

Max Activating Token Index: 921

Text #9

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0459. Min Act: -0.0003

Data Index: 1229466 (C4 (Web Text))

Max Activating Token Index: 197

Text #10

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0464. Min Act: -0.0003

Data Index: 1059130 (C4 (Web Text))

Max Activating Token Index: 291

Text #11

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0468. Min Act: -0.0003

Data Index: 1303396 (C4 (Web Text))

Max Activating Token Index: 574

Text #12

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0473. Min Act: -0.0002

Data Index: 482671 (C4 (Web Text))

Max Activating Token Index: 902

Text #13

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0470. Min Act: -0.0003

Data Index: 117487 (C4 (Web Text))

Max Activating Token Index: 402

Text #14

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0462. Min Act: -0.0003

Data Index: 1383898 (Python Code)

Max Activating Token Index: 26

Text #15

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0455. Min Act: -0.0003

Data Index: 794852 (C4 (Web Text))

Max Activating Token Index: 806

Text #16

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0471. Min Act: -0.0003

Data Index: 552471 (C4 (Web Text))

Max Activating Token Index: 850

Text #17

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0473. Min Act: -0.0003

Data Index: 849192 (C4 (Web Text))

Max Activating Token Index: 749

Text #18

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0462. Min Act: -0.0003

Data Index: 1572070 (Python Code)

Max Activating Token Index: 43

Text #19

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0462. Min Act: -0.0003

Data Index: 1476837 (Python Code)

Max Activating Token Index: 642