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

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

Neuron 4711 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5376. Min Range: -0.5376

Max Act: 0.5376. Min Act: -0.0000

Data Index: 1177155 (C4 (Web Text))

Max Activating Token Index: 990

Text #1

Max Range: 0.5376. Min Range: -0.5376

Max Act: 0.4264. Min Act: -0.0000

Data Index: 467827 (C4 (Web Text))

Max Activating Token Index: 459

Text #2

Max Range: 0.5376. Min Range: -0.5376

Max Act: 0.4197. Min Act: -0.0000

Data Index: 898755 (C4 (Web Text))

Max Activating Token Index: 785

Text #3

Max Range: 0.5376. Min Range: -0.5376

Max Act: 0.4255. Min Act: -0.0000

Data Index: 66841 (C4 (Web Text))

Max Activating Token Index: 372

Text #4

Max Range: 0.5376. Min Range: -0.5376

Max Act: 0.4197. Min Act: -0.0000

Data Index: 1311576 (C4 (Web Text))

Max Activating Token Index: 581

Text #5

Max Range: 0.5376. Min Range: -0.5376

Max Act: 0.3758. Min Act: -0.0000

Data Index: 1317783 (C4 (Web Text))

Max Activating Token Index: 522

Text #6

Max Range: 0.5376. Min Range: -0.5376

Max Act: 0.3687. Min Act: -0.0000

Data Index: 200654 (C4 (Web Text))

Max Activating Token Index: 638

Text #7

Max Range: 0.5376. Min Range: -0.5376

Max Act: 0.3691. Min Act: -0.0000

Data Index: 193664 (C4 (Web Text))

Max Activating Token Index: 991

Text #8

Max Range: 0.5376. Min Range: -0.5376

Max Act: 0.3797. Min Act: -0.0000

Data Index: 1261706 (C4 (Web Text))

Max Activating Token Index: 674

Text #9

Max Range: 0.5376. Min Range: -0.5376

Max Act: 0.3744. Min Act: -0.0000

Data Index: 247435 (C4 (Web Text))

Max Activating Token Index: 277

Text #10

Max Range: 0.5376. Min Range: -0.5376

Max Act: 0.3674. Min Act: -0.0000

Data Index: 1232526 (C4 (Web Text))

Max Activating Token Index: 403

Text #11

Max Range: 0.5376. Min Range: -0.5376

Max Act: 0.3576. Min Act: 0.0000

Data Index: 37466 (C4 (Web Text))

Max Activating Token Index: 575

Text #12

Max Range: 0.5376. Min Range: -0.5376

Max Act: 0.3515. Min Act: -0.0000

Data Index: 97176 (C4 (Web Text))

Max Activating Token Index: 276

Text #13

Max Range: 0.5376. Min Range: -0.5376

Max Act: 0.3626. Min Act: -0.0000

Data Index: 474962 (C4 (Web Text))

Max Activating Token Index: 73

Text #14

Max Range: 0.5376. Min Range: -0.5376

Max Act: 0.3613. Min Act: -0.0000

Data Index: 530136 (C4 (Web Text))

Max Activating Token Index: 927

Text #15

Max Range: 0.5376. Min Range: -0.5376

Max Act: 0.3669. Min Act: 0.0000

Data Index: 1220112 (C4 (Web Text))

Max Activating Token Index: 69

Text #16

Max Range: 0.5376. Min Range: -0.5376

Max Act: 0.3509. Min Act: 0.0000

Data Index: 881146 (C4 (Web Text))

Max Activating Token Index: 789

Text #17

Max Range: 0.5376. Min Range: -0.5376

Max Act: 0.3453. Min Act: -0.0000

Data Index: 673545 (C4 (Web Text))

Max Activating Token Index: 803

Text #18

Max Range: 0.5376. Min Range: -0.5376

Max Act: 0.3448. Min Act: -0.0000

Data Index: 11277 (C4 (Web Text))

Max Activating Token Index: 471

Text #19

Max Range: 0.5376. Min Range: -0.5376

Max Act: 0.3338. Min Act: -0.0000

Data Index: 761622 (C4 (Web Text))

Max Activating Token Index: 429