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

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

Neuron 1621 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: 0.5655. Min Range: -0.5655

Max Act: 0.5655. Min Act: -0.0000

Data Index: 84145 (C4 (Web Text))

Max Activating Token Index: 318

Text #1

Max Range: 0.5655. Min Range: -0.5655

Max Act: 0.5535. Min Act: -0.0000

Data Index: 250863 (C4 (Web Text))

Max Activating Token Index: 362

Text #2

Max Range: 0.5655. Min Range: -0.5655

Max Act: 0.5029. Min Act: -0.0000

Data Index: 425076 (C4 (Web Text))

Max Activating Token Index: 346

Text #3

Max Range: 0.5655. Min Range: -0.5655

Max Act: 0.4449. Min Act: -0.0000

Data Index: 216390 (C4 (Web Text))

Max Activating Token Index: 312

Text #4

Max Range: 0.5655. Min Range: -0.5655

Max Act: 0.4557. Min Act: -0.0000

Data Index: 559652 (C4 (Web Text))

Max Activating Token Index: 406

Text #5

Max Range: 0.5655. Min Range: -0.5655

Max Act: 0.4509. Min Act: -0.0000

Data Index: 1237803 (C4 (Web Text))

Max Activating Token Index: 430

Text #6

Max Range: 0.5655. Min Range: -0.5655

Max Act: 0.4474. Min Act: -0.0000

Data Index: 855499 (C4 (Web Text))

Max Activating Token Index: 871

Text #7

Max Range: 0.5655. Min Range: -0.5655

Max Act: 0.4205. Min Act: -0.0000

Data Index: 1310326 (C4 (Web Text))

Max Activating Token Index: 491

Text #8

Max Range: 0.5655. Min Range: -0.5655

Max Act: 0.4226. Min Act: -0.0000

Data Index: 987523 (C4 (Web Text))

Max Activating Token Index: 878

Text #9

Max Range: 0.5655. Min Range: -0.5655

Max Act: 0.3946. Min Act: -0.0000

Data Index: 629117 (C4 (Web Text))

Max Activating Token Index: 728

Text #10

Max Range: 0.5655. Min Range: -0.5655

Max Act: 0.4385. Min Act: -0.0000

Data Index: 1126868 (C4 (Web Text))

Max Activating Token Index: 268

Text #11

Max Range: 0.5655. Min Range: -0.5655

Max Act: 0.4090. Min Act: -0.0000

Data Index: 253633 (C4 (Web Text))

Max Activating Token Index: 39

Text #12

Max Range: 0.5655. Min Range: -0.5655

Max Act: 0.3725. Min Act: -0.0000

Data Index: 1371476 (Python Code)

Max Activating Token Index: 27

Text #13

Max Range: 0.5655. Min Range: -0.5655

Max Act: 0.3545. Min Act: -0.0000

Data Index: 1157099 (C4 (Web Text))

Max Activating Token Index: 101

Text #14

Max Range: 0.5655. Min Range: -0.5655

Max Act: 0.4049. Min Act: -0.0000

Data Index: 1068631 (C4 (Web Text))

Max Activating Token Index: 769

Text #15

Max Range: 0.5655. Min Range: -0.5655

Max Act: 0.3467. Min Act: -0.0000

Data Index: 949863 (C4 (Web Text))

Max Activating Token Index: 378

Text #16

Max Range: 0.5655. Min Range: -0.5655

Max Act: 0.3871. Min Act: -0.0000

Data Index: 959572 (C4 (Web Text))

Max Activating Token Index: 87

Text #17

Max Range: 0.5655. Min Range: -0.5655

Max Act: 0.3943. Min Act: -0.0000

Data Index: 821825 (C4 (Web Text))

Max Activating Token Index: 289

Text #18

Max Range: 0.5655. Min Range: -0.5655

Max Act: 0.3800. Min Act: -0.0000

Data Index: 74512 (C4 (Web Text))

Max Activating Token Index: 897

Text #19

Max Range: 0.5655. Min Range: -0.5655

Max Act: 0.3529. Min Act: -0.0000

Data Index: 413116 (C4 (Web Text))

Max Activating Token Index: 639