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

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

Neuron 1872 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: 0.0569. Min Range: -0.0569

Max Act: 0.0569. Min Act: -0.0006

Data Index: 792538 (C4 (Web Text))

Max Activating Token Index: 380

Text #1

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0557. Min Act: -0.0006

Data Index: 640984 (C4 (Web Text))

Max Activating Token Index: 987

Text #2

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0543. Min Act: -0.0006

Data Index: 490038 (C4 (Web Text))

Max Activating Token Index: 496

Text #3

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0553. Min Act: -0.0006

Data Index: 160793 (C4 (Web Text))

Max Activating Token Index: 241

Text #4

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0497. Min Act: -0.0006

Data Index: 54159 (C4 (Web Text))

Max Activating Token Index: 879

Text #5

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0482. Min Act: -0.0006

Data Index: 102649 (C4 (Web Text))

Max Activating Token Index: 948

Text #6

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0515. Min Act: -0.0006

Data Index: 1175755 (C4 (Web Text))

Max Activating Token Index: 625

Text #7

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0511. Min Act: -0.0006

Data Index: 115519 (C4 (Web Text))

Max Activating Token Index: 964

Text #8

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0496. Min Act: -0.0006

Data Index: 467610 (C4 (Web Text))

Max Activating Token Index: 652

Text #9

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0490. Min Act: -0.0006

Data Index: 396696 (C4 (Web Text))

Max Activating Token Index: 686

Text #10

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0511. Min Act: -0.0006

Data Index: 1144761 (C4 (Web Text))

Max Activating Token Index: 365

Text #11

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0507. Min Act: -0.0006

Data Index: 846058 (C4 (Web Text))

Max Activating Token Index: 490

Text #12

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0496. Min Act: -0.0006

Data Index: 277220 (C4 (Web Text))

Max Activating Token Index: 329

Text #13

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0506. Min Act: -0.0006

Data Index: 372741 (C4 (Web Text))

Max Activating Token Index: 262

Text #14

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0503. Min Act: -0.0006

Data Index: 948854 (C4 (Web Text))

Max Activating Token Index: 929

Text #15

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0471. Min Act: -0.0006

Data Index: 928540 (C4 (Web Text))

Max Activating Token Index: 835

Text #16

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0481. Min Act: -0.0006

Data Index: 1150989 (C4 (Web Text))

Max Activating Token Index: 980

Text #17

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0481. Min Act: -0.0006

Data Index: 120861 (C4 (Web Text))

Max Activating Token Index: 364

Text #18

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0489. Min Act: -0.0006

Data Index: 1061414 (C4 (Web Text))

Max Activating Token Index: 193

Text #19

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0497. Min Act: -0.0006

Data Index: 1145833 (C4 (Web Text))

Max Activating Token Index: 591