Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1992 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3275. Min Range: -0.3275

Max Act: 0.3275. Min Act: -0.0000

Data Index: 550134 (C4 (Web Text))

Max Activating Token Index: 804

Text #1

Max Range: 0.3275. Min Range: -0.3275

Max Act: 0.2743. Min Act: -0.0000

Data Index: 534169 (C4 (Web Text))

Max Activating Token Index: 751

Text #2

Max Range: 0.3275. Min Range: -0.3275

Max Act: 0.2536. Min Act: -0.0000

Data Index: 149147 (C4 (Web Text))

Max Activating Token Index: 38

Text #3

Max Range: 0.3275. Min Range: -0.3275

Max Act: 0.2025. Min Act: -0.0000

Data Index: 121300 (C4 (Web Text))

Max Activating Token Index: 181

Text #4

Max Range: 0.3275. Min Range: -0.3275

Max Act: 0.1936. Min Act: -0.0000

Data Index: 959126 (C4 (Web Text))

Max Activating Token Index: 712

Text #5

Max Range: 0.3275. Min Range: -0.3275

Max Act: 0.2022. Min Act: -0.0000

Data Index: 1331046 (C4 (Web Text))

Max Activating Token Index: 50

Text #6

Max Range: 0.3275. Min Range: -0.3275

Max Act: 0.1887. Min Act: -0.0000

Data Index: 1237229 (C4 (Web Text))

Max Activating Token Index: 615

Text #7

Max Range: 0.3275. Min Range: -0.3275

Max Act: 0.1798. Min Act: -0.0000

Data Index: 1452564 (Python Code)

Max Activating Token Index: 110

Text #8

Max Range: 0.3275. Min Range: -0.3275

Max Act: 0.1757. Min Act: -0.0000

Data Index: 63193 (C4 (Web Text))

Max Activating Token Index: 423

Text #9

Max Range: 0.3275. Min Range: -0.3275

Max Act: 0.1654. Min Act: -0.0000

Data Index: 569481 (C4 (Web Text))

Max Activating Token Index: 885

Text #10

Max Range: 0.3275. Min Range: -0.3275

Max Act: 0.1600. Min Act: -0.0000

Data Index: 250836 (C4 (Web Text))

Max Activating Token Index: 59

Text #11

Max Range: 0.3275. Min Range: -0.3275

Max Act: 0.1645. Min Act: -0.0000

Data Index: 327959 (C4 (Web Text))

Max Activating Token Index: 672

Text #12

Max Range: 0.3275. Min Range: -0.3275

Max Act: 0.1654. Min Act: -0.0000

Data Index: 649818 (C4 (Web Text))

Max Activating Token Index: 672

Text #13

Max Range: 0.3275. Min Range: -0.3275

Max Act: 0.1649. Min Act: -0.0000

Data Index: 1089588 (C4 (Web Text))

Max Activating Token Index: 380

Text #14

Max Range: 0.3275. Min Range: -0.3275

Max Act: 0.1739. Min Act: -0.0000

Data Index: 111932 (C4 (Web Text))

Max Activating Token Index: 333

Text #15

Max Range: 0.3275. Min Range: -0.3275

Max Act: 0.1614. Min Act: -0.0000

Data Index: 1127672 (C4 (Web Text))

Max Activating Token Index: 130

Text #16

Max Range: 0.3275. Min Range: -0.3275

Max Act: 0.1782. Min Act: -0.0000

Data Index: 493504 (C4 (Web Text))

Max Activating Token Index: 743

Text #17

Max Range: 0.3275. Min Range: -0.3275

Max Act: 0.1587. Min Act: -0.0000

Data Index: 254717 (C4 (Web Text))

Max Activating Token Index: 390

Text #18

Max Range: 0.3275. Min Range: -0.3275

Max Act: 0.1517. Min Act: -0.0000

Data Index: 488726 (C4 (Web Text))

Max Activating Token Index: 404

Text #19

Max Range: 0.3275. Min Range: -0.3275

Max Act: 0.1495. Min Act: -0.0000

Data Index: 1327059 (C4 (Web Text))

Max Activating Token Index: 641