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

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

Neuron 2321 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1351. Min Range: -1.1351

Max Act: 1.1351. Min Act: -0.0000

Data Index: 130542 (C4 (Web Text))

Max Activating Token Index: 858

Text #1

Max Range: 1.1351. Min Range: -1.1351

Max Act: 0.8667. Min Act: -0.0000

Data Index: 357092 (C4 (Web Text))

Max Activating Token Index: 516

Text #2

Max Range: 1.1351. Min Range: -1.1351

Max Act: 0.8648. Min Act: -0.0000

Data Index: 220990 (C4 (Web Text))

Max Activating Token Index: 295

Text #3

Max Range: 1.1351. Min Range: -1.1351

Max Act: 0.7797. Min Act: -0.0000

Data Index: 1300345 (C4 (Web Text))

Max Activating Token Index: 729

Text #4

Max Range: 1.1351. Min Range: -1.1351

Max Act: 0.8508. Min Act: -0.0000

Data Index: 878882 (C4 (Web Text))

Max Activating Token Index: 398

Text #5

Max Range: 1.1351. Min Range: -1.1351

Max Act: 0.8393. Min Act: -0.0000

Data Index: 1098696 (C4 (Web Text))

Max Activating Token Index: 232

Text #6

Max Range: 1.1351. Min Range: -1.1351

Max Act: 0.8314. Min Act: -0.0000

Data Index: 1179145 (C4 (Web Text))

Max Activating Token Index: 828

Text #7

Max Range: 1.1351. Min Range: -1.1351

Max Act: 0.7784. Min Act: -0.0000

Data Index: 217618 (C4 (Web Text))

Max Activating Token Index: 693

Text #8

Max Range: 1.1351. Min Range: -1.1351

Max Act: 0.8010. Min Act: -0.0000

Data Index: 365225 (C4 (Web Text))

Max Activating Token Index: 727

Text #9

Max Range: 1.1351. Min Range: -1.1351

Max Act: 0.7917. Min Act: -0.0000

Data Index: 80030 (C4 (Web Text))

Max Activating Token Index: 195

Text #10

Max Range: 1.1351. Min Range: -1.1351

Max Act: 0.7626. Min Act: -0.0000

Data Index: 15984 (C4 (Web Text))

Max Activating Token Index: 757

Text #11

Max Range: 1.1351. Min Range: -1.1351

Max Act: 0.7793. Min Act: -0.0000

Data Index: 15607 (C4 (Web Text))

Max Activating Token Index: 768

Text #12

Max Range: 1.1351. Min Range: -1.1351

Max Act: 0.8300. Min Act: -0.0000

Data Index: 427490 (C4 (Web Text))

Max Activating Token Index: 831

Text #13

Max Range: 1.1351. Min Range: -1.1351

Max Act: 0.7800. Min Act: -0.0000

Data Index: 260856 (C4 (Web Text))

Max Activating Token Index: 492

Text #14

Max Range: 1.1351. Min Range: -1.1351

Max Act: 0.7827. Min Act: -0.0000

Data Index: 71997 (C4 (Web Text))

Max Activating Token Index: 784

Text #15

Max Range: 1.1351. Min Range: -1.1351

Max Act: 0.7798. Min Act: -0.0000

Data Index: 114281 (C4 (Web Text))

Max Activating Token Index: 859

Text #16

Max Range: 1.1351. Min Range: -1.1351

Max Act: 0.7318. Min Act: -0.0000

Data Index: 542890 (C4 (Web Text))

Max Activating Token Index: 148

Text #17

Max Range: 1.1351. Min Range: -1.1351

Max Act: 0.7495. Min Act: -0.0000

Data Index: 260533 (C4 (Web Text))

Max Activating Token Index: 532

Text #18

Max Range: 1.1351. Min Range: -1.1351

Max Act: 0.7408. Min Act: -0.0000

Data Index: 12570 (C4 (Web Text))

Max Activating Token Index: 280

Text #19

Max Range: 1.1351. Min Range: -1.1351

Max Act: 0.7362. Min Act: -0.0000

Data Index: 146209 (C4 (Web Text))

Max Activating Token Index: 1006