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

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

Neuron 3969 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0559. Min Act: -0.0002

Data Index: 883588 (C4 (Web Text))

Max Activating Token Index: 875

Text #1

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0513. Min Act: -0.0002

Data Index: 893155 (C4 (Web Text))

Max Activating Token Index: 324

Text #2

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0523. Min Act: -0.0002

Data Index: 776827 (C4 (Web Text))

Max Activating Token Index: 464

Text #3

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0499. Min Act: -0.0002

Data Index: 748825 (C4 (Web Text))

Max Activating Token Index: 588

Text #4

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0513. Min Act: -0.0002

Data Index: 696751 (C4 (Web Text))

Max Activating Token Index: 56

Text #5

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0502. Min Act: -0.0002

Data Index: 636325 (C4 (Web Text))

Max Activating Token Index: 784

Text #6

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0449. Min Act: -0.0002

Data Index: 1032549 (C4 (Web Text))

Max Activating Token Index: 927

Text #7

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0492. Min Act: -0.0002

Data Index: 404597 (C4 (Web Text))

Max Activating Token Index: 289

Text #8

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0473. Min Act: -0.0002

Data Index: 893142 (C4 (Web Text))

Max Activating Token Index: 853

Text #9

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0454. Min Act: -0.0002

Data Index: 334694 (C4 (Web Text))

Max Activating Token Index: 621

Text #10

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0451. Min Act: -0.0002

Data Index: 1250196 (C4 (Web Text))

Max Activating Token Index: 561

Text #11

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0427. Min Act: -0.0002

Data Index: 758648 (C4 (Web Text))

Max Activating Token Index: 262

Text #12

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0436. Min Act: -0.0002

Data Index: 483288 (C4 (Web Text))

Max Activating Token Index: 634

Text #13

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0427. Min Act: -0.0002

Data Index: 1232784 (C4 (Web Text))

Max Activating Token Index: 819

Text #14

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0419. Min Act: -0.0002

Data Index: 1127235 (C4 (Web Text))

Max Activating Token Index: 1017

Text #15

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0444. Min Act: -0.0002

Data Index: 463308 (C4 (Web Text))

Max Activating Token Index: 394

Text #16

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0425. Min Act: -0.0002

Data Index: 1050707 (C4 (Web Text))

Max Activating Token Index: 74

Text #17

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0456. Min Act: -0.0002

Data Index: 1229990 (C4 (Web Text))

Max Activating Token Index: 423

Text #18

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0435. Min Act: -0.0002

Data Index: 1209202 (C4 (Web Text))

Max Activating Token Index: 886

Text #19

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0399. Min Act: -0.0002

Data Index: 995595 (C4 (Web Text))

Max Activating Token Index: 636