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

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

Neuron 74 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.7988. Min Act: -0.0000

Data Index: 1077702 (C4 (Web Text))

Max Activating Token Index: 765

Text #1

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.6783. Min Act: 0.0000

Data Index: 1135925 (C4 (Web Text))

Max Activating Token Index: 364

Text #2

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.7108. Min Act: -0.0000

Data Index: 852056 (C4 (Web Text))

Max Activating Token Index: 466

Text #3

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.6659. Min Act: 0.0000

Data Index: 333373 (C4 (Web Text))

Max Activating Token Index: 429

Text #4

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.5664. Min Act: -0.0000

Data Index: 40262 (C4 (Web Text))

Max Activating Token Index: 827

Text #5

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.5906. Min Act: -0.0000

Data Index: 392555 (C4 (Web Text))

Max Activating Token Index: 676

Text #6

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.5646. Min Act: -0.0000

Data Index: 693218 (C4 (Web Text))

Max Activating Token Index: 258

Text #7

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.5354. Min Act: -0.0000

Data Index: 839009 (C4 (Web Text))

Max Activating Token Index: 458

Text #8

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.5308. Min Act: -0.0000

Data Index: 327479 (C4 (Web Text))

Max Activating Token Index: 701

Text #9

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.5090. Min Act: 0.0000

Data Index: 424961 (C4 (Web Text))

Max Activating Token Index: 928

Text #10

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.4869. Min Act: -0.0000

Data Index: 1556685 (Python Code)

Max Activating Token Index: 446

Text #11

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.4885. Min Act: -0.0000

Data Index: 176271 (C4 (Web Text))

Max Activating Token Index: 538

Text #12

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.5660. Min Act: -0.0000

Data Index: 166980 (C4 (Web Text))

Max Activating Token Index: 786

Text #13

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.4990. Min Act: -0.0000

Data Index: 1038580 (C4 (Web Text))

Max Activating Token Index: 719

Text #14

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.4905. Min Act: -0.0000

Data Index: 560890 (C4 (Web Text))

Max Activating Token Index: 597

Text #15

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.4293. Min Act: -0.0000

Data Index: 1447782 (Python Code)

Max Activating Token Index: 925

Text #16

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.4522. Min Act: -0.0000

Data Index: 545460 (C4 (Web Text))

Max Activating Token Index: 967

Text #17

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.4551. Min Act: -0.0000

Data Index: 799992 (C4 (Web Text))

Max Activating Token Index: 62

Text #18

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.4519. Min Act: 0.0000

Data Index: 740974 (C4 (Web Text))

Max Activating Token Index: 124

Text #19

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.4234. Min Act: -0.0000

Data Index: 335461 (C4 (Web Text))

Max Activating Token Index: 52