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

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

Neuron 3312 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1521. Min Range: -1.1521

Max Act: 1.1521. Min Act: -0.0000

Data Index: 1457816 (Python Code)

Max Activating Token Index: 212

Text #1

Max Range: 1.1521. Min Range: -1.1521

Max Act: 1.0954. Min Act: -0.0000

Data Index: 1215420 (C4 (Web Text))

Max Activating Token Index: 662

Text #2

Max Range: 1.1521. Min Range: -1.1521

Max Act: 1.1353. Min Act: -0.0000

Data Index: 1120756 (C4 (Web Text))

Max Activating Token Index: 304

Text #3

Max Range: 1.1521. Min Range: -1.1521

Max Act: 1.1254. Min Act: -0.0000

Data Index: 283088 (C4 (Web Text))

Max Activating Token Index: 806

Text #4

Max Range: 1.1521. Min Range: -1.1521

Max Act: 1.0398. Min Act: -0.0000

Data Index: 398658 (C4 (Web Text))

Max Activating Token Index: 91

Text #5

Max Range: 1.1521. Min Range: -1.1521

Max Act: 0.9923. Min Act: -0.0000

Data Index: 620798 (C4 (Web Text))

Max Activating Token Index: 89

Text #6

Max Range: 1.1521. Min Range: -1.1521

Max Act: 0.9421. Min Act: -0.0000

Data Index: 115028 (C4 (Web Text))

Max Activating Token Index: 707

Text #7

Max Range: 1.1521. Min Range: -1.1521

Max Act: 0.9966. Min Act: -0.0000

Data Index: 132563 (C4 (Web Text))

Max Activating Token Index: 155

Text #8

Max Range: 1.1521. Min Range: -1.1521

Max Act: 0.9996. Min Act: -0.0000

Data Index: 297578 (C4 (Web Text))

Max Activating Token Index: 325

Text #9

Max Range: 1.1521. Min Range: -1.1521

Max Act: 0.9037. Min Act: -0.0000

Data Index: 834297 (C4 (Web Text))

Max Activating Token Index: 919

Text #10

Max Range: 1.1521. Min Range: -1.1521

Max Act: 0.9584. Min Act: -0.0000

Data Index: 250877 (C4 (Web Text))

Max Activating Token Index: 633

Text #11

Max Range: 1.1521. Min Range: -1.1521

Max Act: 0.9479. Min Act: -0.0000

Data Index: 651153 (C4 (Web Text))

Max Activating Token Index: 454

Text #12

Max Range: 1.1521. Min Range: -1.1521

Max Act: 1.0023. Min Act: -0.0000

Data Index: 9318 (C4 (Web Text))

Max Activating Token Index: 297

Text #13

Max Range: 1.1521. Min Range: -1.1521

Max Act: 0.9835. Min Act: -0.0000

Data Index: 469727 (C4 (Web Text))

Max Activating Token Index: 141

Text #14

Max Range: 1.1521. Min Range: -1.1521

Max Act: 0.9143. Min Act: -0.0000

Data Index: 472122 (C4 (Web Text))

Max Activating Token Index: 234

Text #15

Max Range: 1.1521. Min Range: -1.1521

Max Act: 0.8938. Min Act: -0.0000

Data Index: 9175 (C4 (Web Text))

Max Activating Token Index: 656

Text #16

Max Range: 1.1521. Min Range: -1.1521

Max Act: 0.9406. Min Act: -0.0000

Data Index: 1274461 (C4 (Web Text))

Max Activating Token Index: 347

Text #17

Max Range: 1.1521. Min Range: -1.1521

Max Act: 0.8751. Min Act: -0.0000

Data Index: 251584 (C4 (Web Text))

Max Activating Token Index: 870

Text #18

Max Range: 1.1521. Min Range: -1.1521

Max Act: 0.8788. Min Act: 0.0000

Data Index: 1081790 (C4 (Web Text))

Max Activating Token Index: 707

Text #19

Max Range: 1.1521. Min Range: -1.1521

Max Act: 0.8758. Min Act: -0.0000

Data Index: 1294465 (C4 (Web Text))

Max Activating Token Index: 595