Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 3 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0554. Min Act: -0.0005

Data Index: 510397 (C4 (Web Text))

Max Activating Token Index: 93

Text #1

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0544. Min Act: -0.0005

Data Index: 871330 (C4 (Web Text))

Max Activating Token Index: 343

Text #2

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0553. Min Act: -0.0005

Data Index: 1125601 (C4 (Web Text))

Max Activating Token Index: 680

Text #3

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0503. Min Act: -0.0005

Data Index: 903422 (C4 (Web Text))

Max Activating Token Index: 457

Text #4

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0522. Min Act: -0.0005

Data Index: 561988 (C4 (Web Text))

Max Activating Token Index: 29

Text #5

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0496. Min Act: -0.0005

Data Index: 21312 (C4 (Web Text))

Max Activating Token Index: 969

Text #6

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0466. Min Act: -0.0005

Data Index: 77264 (C4 (Web Text))

Max Activating Token Index: 460

Text #7

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0479. Min Act: -0.0005

Data Index: 1317031 (C4 (Web Text))

Max Activating Token Index: 120

Text #8

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0490. Min Act: -0.0005

Data Index: 580987 (C4 (Web Text))

Max Activating Token Index: 169

Text #9

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0477. Min Act: -0.0005

Data Index: 300010 (C4 (Web Text))

Max Activating Token Index: 928

Text #10

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0466. Min Act: -0.0005

Data Index: 670332 (C4 (Web Text))

Max Activating Token Index: 864

Text #11

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0471. Min Act: -0.0005

Data Index: 497510 (C4 (Web Text))

Max Activating Token Index: 1014

Text #12

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0471. Min Act: -0.0005

Data Index: 211957 (C4 (Web Text))

Max Activating Token Index: 264

Text #13

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0472. Min Act: -0.0005

Data Index: 950570 (C4 (Web Text))

Max Activating Token Index: 886

Text #14

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0473. Min Act: -0.0005

Data Index: 843102 (C4 (Web Text))

Max Activating Token Index: 933

Text #15

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0431. Min Act: -0.0005

Data Index: 820285 (C4 (Web Text))

Max Activating Token Index: 657

Text #16

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0448. Min Act: -0.0005

Data Index: 624285 (C4 (Web Text))

Max Activating Token Index: 116

Text #17

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0462. Min Act: -0.0005

Data Index: 149353 (C4 (Web Text))

Max Activating Token Index: 315

Text #18

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0441. Min Act: -0.0005

Data Index: 264677 (C4 (Web Text))

Max Activating Token Index: 488

Text #19

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0448. Min Act: -0.0005

Data Index: 456165 (C4 (Web Text))

Max Activating Token Index: 785