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

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

Neuron 1492 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: 0.1983. Min Range: -0.1983

Max Act: 0.1983. Min Act: -0.0000

Data Index: 257654 (C4 (Web Text))

Max Activating Token Index: 280

Text #1

Max Range: 0.1983. Min Range: -0.1983

Max Act: 0.1654. Min Act: -0.0000

Data Index: 238779 (C4 (Web Text))

Max Activating Token Index: 809

Text #2

Max Range: 0.1983. Min Range: -0.1983

Max Act: 0.1494. Min Act: -0.0000

Data Index: 854030 (C4 (Web Text))

Max Activating Token Index: 904

Text #3

Max Range: 0.1983. Min Range: -0.1983

Max Act: 0.1583. Min Act: -0.0000

Data Index: 995984 (C4 (Web Text))

Max Activating Token Index: 915

Text #4

Max Range: 0.1983. Min Range: -0.1983

Max Act: 0.1533. Min Act: -0.0000

Data Index: 633731 (C4 (Web Text))

Max Activating Token Index: 116

Text #5

Max Range: 0.1983. Min Range: -0.1983

Max Act: 0.1480. Min Act: -0.0000

Data Index: 29042 (C4 (Web Text))

Max Activating Token Index: 265

Text #6

Max Range: 0.1983. Min Range: -0.1983

Max Act: 0.1434. Min Act: -0.0000

Data Index: 1653410 (Python Code)

Max Activating Token Index: 567

Text #7

Max Range: 0.1983. Min Range: -0.1983

Max Act: 0.1515. Min Act: -0.0000

Data Index: 1229651 (C4 (Web Text))

Max Activating Token Index: 214

Text #8

Max Range: 0.1983. Min Range: -0.1983

Max Act: 0.1454. Min Act: -0.0000

Data Index: 1195829 (C4 (Web Text))

Max Activating Token Index: 719

Text #9

Max Range: 0.1983. Min Range: -0.1983

Max Act: 0.1501. Min Act: -0.0000

Data Index: 131065 (C4 (Web Text))

Max Activating Token Index: 209

Text #10

Max Range: 0.1983. Min Range: -0.1983

Max Act: 0.1455. Min Act: -0.0000

Data Index: 150605 (C4 (Web Text))

Max Activating Token Index: 718

Text #11

Max Range: 0.1983. Min Range: -0.1983

Max Act: 0.1479. Min Act: -0.0000

Data Index: 448221 (C4 (Web Text))

Max Activating Token Index: 455

Text #12

Max Range: 0.1983. Min Range: -0.1983

Max Act: 0.1423. Min Act: -0.0000

Data Index: 964692 (C4 (Web Text))

Max Activating Token Index: 430

Text #13

Max Range: 0.1983. Min Range: -0.1983

Max Act: 0.1402. Min Act: -0.0000

Data Index: 468949 (C4 (Web Text))

Max Activating Token Index: 512

Text #14

Max Range: 0.1983. Min Range: -0.1983

Max Act: 0.1383. Min Act: -0.0000

Data Index: 48947 (C4 (Web Text))

Max Activating Token Index: 76

Text #15

Max Range: 0.1983. Min Range: -0.1983

Max Act: 0.1200. Min Act: -0.0000

Data Index: 195950 (C4 (Web Text))

Max Activating Token Index: 540

Text #16

Max Range: 0.1983. Min Range: -0.1983

Max Act: 0.1433. Min Act: -0.0000

Data Index: 318347 (C4 (Web Text))

Max Activating Token Index: 929

Text #17

Max Range: 0.1983. Min Range: -0.1983

Max Act: 0.1255. Min Act: -0.0000

Data Index: 616594 (C4 (Web Text))

Max Activating Token Index: 906

Text #18

Max Range: 0.1983. Min Range: -0.1983

Max Act: 0.1283. Min Act: -0.0000

Data Index: 1006144 (C4 (Web Text))

Max Activating Token Index: 827

Text #19

Max Range: 0.1983. Min Range: -0.1983

Max Act: 0.1263. Min Act: -0.0000

Data Index: 349044 (C4 (Web Text))

Max Activating Token Index: 849