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

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

Neuron 2362 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: 3.4562. Min Range: -3.4562

Max Act: 3.4562. Min Act: -0.0000

Data Index: 813386 (C4 (Web Text))

Max Activating Token Index: 750

Text #1

Max Range: 3.4562. Min Range: -3.4562

Max Act: 2.4510. Min Act: -0.0000

Data Index: 303359 (C4 (Web Text))

Max Activating Token Index: 590

Text #2

Max Range: 3.4562. Min Range: -3.4562

Max Act: 2.1633. Min Act: -0.0000

Data Index: 919059 (C4 (Web Text))

Max Activating Token Index: 914

Text #3

Max Range: 3.4562. Min Range: -3.4562

Max Act: 1.9404. Min Act: -0.0000

Data Index: 140443 (C4 (Web Text))

Max Activating Token Index: 763

Text #4

Max Range: 3.4562. Min Range: -3.4562

Max Act: 2.0104. Min Act: -0.0000

Data Index: 1601153 (Python Code)

Max Activating Token Index: 855

Text #5

Max Range: 3.4562. Min Range: -3.4562

Max Act: 1.6527. Min Act: -0.0000

Data Index: 1434131 (Python Code)

Max Activating Token Index: 21

Text #6

Max Range: 3.4562. Min Range: -3.4562

Max Act: 1.8640. Min Act: -0.0000

Data Index: 1586982 (Python Code)

Max Activating Token Index: 237

Text #7

Max Range: 3.4562. Min Range: -3.4562

Max Act: 1.3178. Min Act: -0.0000

Data Index: 377814 (C4 (Web Text))

Max Activating Token Index: 241

Text #8

Max Range: 3.4562. Min Range: -3.4562

Max Act: 1.5542. Min Act: -0.0000

Data Index: 1517161 (Python Code)

Max Activating Token Index: 1012

Text #9

Max Range: 3.4562. Min Range: -3.4562

Max Act: 1.3143. Min Act: -0.0000

Data Index: 452980 (C4 (Web Text))

Max Activating Token Index: 834

Text #10

Max Range: 3.4562. Min Range: -3.4562

Max Act: 1.3007. Min Act: -0.0000

Data Index: 770406 (C4 (Web Text))

Max Activating Token Index: 630

Text #11

Max Range: 3.4562. Min Range: -3.4562

Max Act: 1.3919. Min Act: -0.0000

Data Index: 1574678 (Python Code)

Max Activating Token Index: 144

Text #12

Max Range: 3.4562. Min Range: -3.4562

Max Act: 1.3735. Min Act: 0.0000

Data Index: 1566049 (Python Code)

Max Activating Token Index: 36

Text #13

Max Range: 3.4562. Min Range: -3.4562

Max Act: 1.3383. Min Act: -0.0000

Data Index: 1004651 (C4 (Web Text))

Max Activating Token Index: 139

Text #14

Max Range: 3.4562. Min Range: -3.4562

Max Act: 1.3275. Min Act: -0.0000

Data Index: 1595419 (Python Code)

Max Activating Token Index: 156

Text #15

Max Range: 3.4562. Min Range: -3.4562

Max Act: 1.2249. Min Act: -0.0000

Data Index: 583260 (C4 (Web Text))

Max Activating Token Index: 668

Text #16

Max Range: 3.4562. Min Range: -3.4562

Max Act: 1.3317. Min Act: -0.0000

Data Index: 295959 (C4 (Web Text))

Max Activating Token Index: 990

Text #17

Max Range: 3.4562. Min Range: -3.4562

Max Act: 1.2828. Min Act: 0.0001

Data Index: 1543373 (Python Code)

Max Activating Token Index: 379

Text #18

Max Range: 3.4562. Min Range: -3.4562

Max Act: 1.2653. Min Act: 0.0001

Data Index: 1569576 (Python Code)

Max Activating Token Index: 943

Text #19

Max Range: 3.4562. Min Range: -3.4562

Max Act: 1.2556. Min Act: -0.0000

Data Index: 878946 (C4 (Web Text))

Max Activating Token Index: 549