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

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

Neuron 3359 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: 0.0688. Min Range: -0.0688

Max Act: 0.0682. Min Act: -0.0002

Data Index: 91019 (C4 (Web Text))

Max Activating Token Index: 430

Text #1

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0661. Min Act: -0.0003

Data Index: 704586 (C4 (Web Text))

Max Activating Token Index: 874

Text #2

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0688. Min Act: -0.0002

Data Index: 1100118 (C4 (Web Text))

Max Activating Token Index: 277

Text #3

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0602. Min Act: -0.0003

Data Index: 260987 (C4 (Web Text))

Max Activating Token Index: 180

Text #4

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0574. Min Act: -0.0003

Data Index: 1125021 (C4 (Web Text))

Max Activating Token Index: 792

Text #5

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0537. Min Act: -0.0003

Data Index: 24806 (C4 (Web Text))

Max Activating Token Index: 486

Text #6

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0521. Min Act: -0.0002

Data Index: 763014 (C4 (Web Text))

Max Activating Token Index: 960

Text #7

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0499. Min Act: -0.0003

Data Index: 22192 (C4 (Web Text))

Max Activating Token Index: 97

Text #8

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0519. Min Act: -0.0003

Data Index: 15062 (C4 (Web Text))

Max Activating Token Index: 453

Text #9

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0509. Min Act: -0.0003

Data Index: 673779 (C4 (Web Text))

Max Activating Token Index: 809

Text #10

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0506. Min Act: -0.0003

Data Index: 536317 (C4 (Web Text))

Max Activating Token Index: 175

Text #11

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0512. Min Act: -0.0002

Data Index: 249109 (C4 (Web Text))

Max Activating Token Index: 213

Text #12

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0492. Min Act: -0.0003

Data Index: 1336104 (C4 (Web Text))

Max Activating Token Index: 408

Text #13

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0480. Min Act: -0.0002

Data Index: 900616 (C4 (Web Text))

Max Activating Token Index: 503

Text #14

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0487. Min Act: -0.0002

Data Index: 658872 (C4 (Web Text))

Max Activating Token Index: 765

Text #15

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0490. Min Act: -0.0003

Data Index: 437836 (C4 (Web Text))

Max Activating Token Index: 66

Text #16

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0483. Min Act: -0.0002

Data Index: 338844 (C4 (Web Text))

Max Activating Token Index: 505

Text #17

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0483. Min Act: -0.0003

Data Index: 84476 (C4 (Web Text))

Max Activating Token Index: 244

Text #18

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0466. Min Act: -0.0003

Data Index: 686616 (C4 (Web Text))

Max Activating Token Index: 176

Text #19

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0481. Min Act: -0.0002

Data Index: 1101444 (C4 (Web Text))

Max Activating Token Index: 191