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

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

Neuron 5784 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3382. Min Range: -0.3382

Max Act: 0.3382. Min Act: -0.0000

Data Index: 1276466 (C4 (Web Text))

Max Activating Token Index: 268

Text #1

Max Range: 0.3382. Min Range: -0.3382

Max Act: 0.3371. Min Act: -0.0000

Data Index: 9609 (C4 (Web Text))

Max Activating Token Index: 662

Text #2

Max Range: 0.3382. Min Range: -0.3382

Max Act: 0.3054. Min Act: -0.0000

Data Index: 126447 (C4 (Web Text))

Max Activating Token Index: 809

Text #3

Max Range: 0.3382. Min Range: -0.3382

Max Act: 0.2895. Min Act: -0.0000

Data Index: 401721 (C4 (Web Text))

Max Activating Token Index: 428

Text #4

Max Range: 0.3382. Min Range: -0.3382

Max Act: 0.2864. Min Act: -0.0000

Data Index: 1317568 (C4 (Web Text))

Max Activating Token Index: 269

Text #5

Max Range: 0.3382. Min Range: -0.3382

Max Act: 0.2329. Min Act: -0.0000

Data Index: 783395 (C4 (Web Text))

Max Activating Token Index: 414

Text #6

Max Range: 0.3382. Min Range: -0.3382

Max Act: 0.2396. Min Act: -0.0000

Data Index: 851406 (C4 (Web Text))

Max Activating Token Index: 968

Text #7

Max Range: 0.3382. Min Range: -0.3382

Max Act: 0.2343. Min Act: -0.0000

Data Index: 613680 (C4 (Web Text))

Max Activating Token Index: 535

Text #8

Max Range: 0.3382. Min Range: -0.3382

Max Act: 0.2100. Min Act: -0.0000

Data Index: 1225249 (C4 (Web Text))

Max Activating Token Index: 590

Text #9

Max Range: 0.3382. Min Range: -0.3382

Max Act: 0.2234. Min Act: -0.0000

Data Index: 30514 (C4 (Web Text))

Max Activating Token Index: 402

Text #10

Max Range: 0.3382. Min Range: -0.3382

Max Act: 0.2156. Min Act: -0.0000

Data Index: 538260 (C4 (Web Text))

Max Activating Token Index: 881

Text #11

Max Range: 0.3382. Min Range: -0.3382

Max Act: 0.1970. Min Act: 0.0000

Data Index: 1150003 (C4 (Web Text))

Max Activating Token Index: 92

Text #12

Max Range: 0.3382. Min Range: -0.3382

Max Act: 0.2103. Min Act: -0.0000

Data Index: 560917 (C4 (Web Text))

Max Activating Token Index: 109

Text #13

Max Range: 0.3382. Min Range: -0.3382

Max Act: 0.2025. Min Act: -0.0000

Data Index: 30127 (C4 (Web Text))

Max Activating Token Index: 452

Text #14

Max Range: 0.3382. Min Range: -0.3382

Max Act: 0.2027. Min Act: -0.0000

Data Index: 720005 (C4 (Web Text))

Max Activating Token Index: 693

Text #15

Max Range: 0.3382. Min Range: -0.3382

Max Act: 0.2159. Min Act: -0.0000

Data Index: 271221 (C4 (Web Text))

Max Activating Token Index: 857

Text #16

Max Range: 0.3382. Min Range: -0.3382

Max Act: 0.2023. Min Act: -0.0000

Data Index: 10649 (C4 (Web Text))

Max Activating Token Index: 285

Text #17

Max Range: 0.3382. Min Range: -0.3382

Max Act: 0.1991. Min Act: -0.0000

Data Index: 178296 (C4 (Web Text))

Max Activating Token Index: 569

Text #18

Max Range: 0.3382. Min Range: -0.3382

Max Act: 0.1958. Min Act: -0.0000

Data Index: 85576 (C4 (Web Text))

Max Activating Token Index: 893

Text #19

Max Range: 0.3382. Min Range: -0.3382

Max Act: 0.1838. Min Act: -0.0000

Data Index: 913357 (C4 (Web Text))

Max Activating Token Index: 907