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

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

Neuron 2697 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.1333. Min Range: -6.1333

Max Act: 6.1333. Min Act: -0.0001

Data Index: 306638 (C4 (Web Text))

Max Activating Token Index: 440

Text #1

Max Range: 6.1333. Min Range: -6.1333

Max Act: 6.0335. Min Act: -0.0001

Data Index: 1292906 (C4 (Web Text))

Max Activating Token Index: 333

Text #2

Max Range: 6.1333. Min Range: -6.1333

Max Act: 5.2909. Min Act: -0.0001

Data Index: 628086 (C4 (Web Text))

Max Activating Token Index: 481

Text #3

Max Range: 6.1333. Min Range: -6.1333

Max Act: 5.3994. Min Act: -0.0000

Data Index: 543690 (C4 (Web Text))

Max Activating Token Index: 1022

Text #4

Max Range: 6.1333. Min Range: -6.1333

Max Act: 4.7138. Min Act: -0.0000

Data Index: 216810 (C4 (Web Text))

Max Activating Token Index: 821

Text #5

Max Range: 6.1333. Min Range: -6.1333

Max Act: 4.1394. Min Act: -0.0000

Data Index: 968489 (C4 (Web Text))

Max Activating Token Index: 703

Text #6

Max Range: 6.1333. Min Range: -6.1333

Max Act: 4.2669. Min Act: -0.0000

Data Index: 1229469 (C4 (Web Text))

Max Activating Token Index: 534

Text #7

Max Range: 6.1333. Min Range: -6.1333

Max Act: 3.9799. Min Act: -0.0000

Data Index: 820772 (C4 (Web Text))

Max Activating Token Index: 417

Text #8

Max Range: 6.1333. Min Range: -6.1333

Max Act: 3.8896. Min Act: -0.0000

Data Index: 549888 (C4 (Web Text))

Max Activating Token Index: 134

Text #9

Max Range: 6.1333. Min Range: -6.1333

Max Act: 3.8673. Min Act: -0.0000

Data Index: 619584 (C4 (Web Text))

Max Activating Token Index: 1001

Text #10

Max Range: 6.1333. Min Range: -6.1333

Max Act: 3.5801. Min Act: -0.0001

Data Index: 672285 (C4 (Web Text))

Max Activating Token Index: 252

Text #11

Max Range: 6.1333. Min Range: -6.1333

Max Act: 3.8170. Min Act: -0.0000

Data Index: 184339 (C4 (Web Text))

Max Activating Token Index: 908

Text #12

Max Range: 6.1333. Min Range: -6.1333

Max Act: 4.1672. Min Act: -0.0000

Data Index: 128602 (C4 (Web Text))

Max Activating Token Index: 840

Text #13

Max Range: 6.1333. Min Range: -6.1333

Max Act: 3.9236. Min Act: -0.0000

Data Index: 685024 (C4 (Web Text))

Max Activating Token Index: 604

Text #14

Max Range: 6.1333. Min Range: -6.1333

Max Act: 3.0878. Min Act: -0.0000

Data Index: 725226 (C4 (Web Text))

Max Activating Token Index: 866

Text #15

Max Range: 6.1333. Min Range: -6.1333

Max Act: 3.7846. Min Act: -0.0000

Data Index: 495498 (C4 (Web Text))

Max Activating Token Index: 761

Text #16

Max Range: 6.1333. Min Range: -6.1333

Max Act: 3.7787. Min Act: -0.0000

Data Index: 275019 (C4 (Web Text))

Max Activating Token Index: 640

Text #17

Max Range: 6.1333. Min Range: -6.1333

Max Act: 3.5339. Min Act: -0.0000

Data Index: 261524 (C4 (Web Text))

Max Activating Token Index: 924

Text #18

Max Range: 6.1333. Min Range: -6.1333

Max Act: 3.5219. Min Act: -0.0000

Data Index: 728907 (C4 (Web Text))

Max Activating Token Index: 289

Text #19

Max Range: 6.1333. Min Range: -6.1333

Max Act: 3.5173. Min Act: -0.0001

Data Index: 272935 (C4 (Web Text))

Max Activating Token Index: 27