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

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

Neuron 4226 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: 0.0523. Min Range: -0.0523

Max Act: 0.0523. Min Act: -0.0002

Data Index: 506999 (C4 (Web Text))

Max Activating Token Index: 536

Text #1

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0518. Min Act: -0.0003

Data Index: 989524 (C4 (Web Text))

Max Activating Token Index: 255

Text #2

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0515. Min Act: -0.0003

Data Index: 17302 (C4 (Web Text))

Max Activating Token Index: 193

Text #3

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0493. Min Act: -0.0003

Data Index: 1289263 (C4 (Web Text))

Max Activating Token Index: 895

Text #4

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0509. Min Act: -0.0003

Data Index: 800809 (C4 (Web Text))

Max Activating Token Index: 356

Text #5

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0497. Min Act: -0.0002

Data Index: 423940 (C4 (Web Text))

Max Activating Token Index: 1005

Text #6

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0496. Min Act: -0.0003

Data Index: 877734 (C4 (Web Text))

Max Activating Token Index: 252

Text #7

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0488. Min Act: -0.0003

Data Index: 347973 (C4 (Web Text))

Max Activating Token Index: 744

Text #8

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0470. Min Act: -0.0003

Data Index: 393673 (C4 (Web Text))

Max Activating Token Index: 648

Text #9

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0474. Min Act: -0.0003

Data Index: 492807 (C4 (Web Text))

Max Activating Token Index: 472

Text #10

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0471. Min Act: -0.0002

Data Index: 1337587 (C4 (Web Text))

Max Activating Token Index: 709

Text #11

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0476. Min Act: -0.0003

Data Index: 625938 (C4 (Web Text))

Max Activating Token Index: 392

Text #12

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0473. Min Act: -0.0003

Data Index: 868783 (C4 (Web Text))

Max Activating Token Index: 935

Text #13

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0462. Min Act: -0.0003

Data Index: 1128973 (C4 (Web Text))

Max Activating Token Index: 41

Text #14

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0460. Min Act: -0.0003

Data Index: 1307304 (C4 (Web Text))

Max Activating Token Index: 298

Text #15

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0457. Min Act: -0.0003

Data Index: 880584 (C4 (Web Text))

Max Activating Token Index: 645

Text #16

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0472. Min Act: -0.0003

Data Index: 549301 (C4 (Web Text))

Max Activating Token Index: 637

Text #17

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0465. Min Act: -0.0003

Data Index: 1060821 (C4 (Web Text))

Max Activating Token Index: 844

Text #18

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0443. Min Act: -0.0003

Data Index: 1059950 (C4 (Web Text))

Max Activating Token Index: 284

Text #19

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0449. Min Act: -0.0003

Data Index: 307787 (C4 (Web Text))

Max Activating Token Index: 773