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

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

Neuron 1773 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: 2.1319. Min Range: -2.1319

Max Act: 2.1319. Min Act: -0.0000

Data Index: 219110 (C4 (Web Text))

Max Activating Token Index: 739

Text #1

Max Range: 2.1319. Min Range: -2.1319

Max Act: 1.9120. Min Act: -0.0000

Data Index: 121371 (C4 (Web Text))

Max Activating Token Index: 147

Text #2

Max Range: 2.1319. Min Range: -2.1319

Max Act: 1.9948. Min Act: -0.0000

Data Index: 953216 (C4 (Web Text))

Max Activating Token Index: 415

Text #3

Max Range: 2.1319. Min Range: -2.1319

Max Act: 1.8827. Min Act: -0.0000

Data Index: 1403670 (Python Code)

Max Activating Token Index: 1007

Text #4

Max Range: 2.1319. Min Range: -2.1319

Max Act: 1.7822. Min Act: -0.0000

Data Index: 37932 (C4 (Web Text))

Max Activating Token Index: 1000

Text #5

Max Range: 2.1319. Min Range: -2.1319

Max Act: 1.8682. Min Act: -0.0000

Data Index: 1415601 (Python Code)

Max Activating Token Index: 479

Text #6

Max Range: 2.1319. Min Range: -2.1319

Max Act: 1.8579. Min Act: -0.0000

Data Index: 1313648 (C4 (Web Text))

Max Activating Token Index: 103

Text #7

Max Range: 2.1319. Min Range: -2.1319

Max Act: 1.8445. Min Act: -0.0000

Data Index: 1433016 (Python Code)

Max Activating Token Index: 695

Text #8

Max Range: 2.1319. Min Range: -2.1319

Max Act: 1.9458. Min Act: -0.0000

Data Index: 180312 (C4 (Web Text))

Max Activating Token Index: 1010

Text #9

Max Range: 2.1319. Min Range: -2.1319

Max Act: 1.8484. Min Act: -0.0000

Data Index: 1597770 (Python Code)

Max Activating Token Index: 731

Text #10

Max Range: 2.1319. Min Range: -2.1319

Max Act: 1.8494. Min Act: -0.0000

Data Index: 1609606 (Python Code)

Max Activating Token Index: 601

Text #11

Max Range: 2.1319. Min Range: -2.1319

Max Act: 1.8359. Min Act: -0.0000

Data Index: 646501 (C4 (Web Text))

Max Activating Token Index: 196

Text #12

Max Range: 2.1319. Min Range: -2.1319

Max Act: 1.8223. Min Act: -0.0000

Data Index: 1319465 (C4 (Web Text))

Max Activating Token Index: 655

Text #13

Max Range: 2.1319. Min Range: -2.1319

Max Act: 1.7362. Min Act: -0.0000

Data Index: 140578 (C4 (Web Text))

Max Activating Token Index: 474

Text #14

Max Range: 2.1319. Min Range: -2.1319

Max Act: 1.8035. Min Act: -0.0000

Data Index: 1434883 (Python Code)

Max Activating Token Index: 762

Text #15

Max Range: 2.1319. Min Range: -2.1319

Max Act: 1.8933. Min Act: -0.0000

Data Index: 1379350 (Python Code)

Max Activating Token Index: 632

Text #16

Max Range: 2.1319. Min Range: -2.1319

Max Act: 1.8795. Min Act: -0.0000

Data Index: 817908 (C4 (Web Text))

Max Activating Token Index: 598

Text #17

Max Range: 2.1319. Min Range: -2.1319

Max Act: 1.8016. Min Act: -0.0000

Data Index: 1571797 (Python Code)

Max Activating Token Index: 699

Text #18

Max Range: 2.1319. Min Range: -2.1319

Max Act: 1.8856. Min Act: -0.0000

Data Index: 1511799 (Python Code)

Max Activating Token Index: 128

Text #19

Max Range: 2.1319. Min Range: -2.1319

Max Act: 1.6888. Min Act: -0.0000

Data Index: 1528679 (Python Code)

Max Activating Token Index: 179