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

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

Neuron 1135 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1720. Min Range: -2.1720

Max Act: 2.1720. Min Act: -0.0000

Data Index: 1270221 (C4 (Web Text))

Max Activating Token Index: 62

Text #1

Max Range: 2.1720. Min Range: -2.1720

Max Act: 1.8299. Min Act: -0.0001

Data Index: 1041200 (C4 (Web Text))

Max Activating Token Index: 236

Text #2

Max Range: 2.1720. Min Range: -2.1720

Max Act: 1.6658. Min Act: -0.0000

Data Index: 861865 (C4 (Web Text))

Max Activating Token Index: 726

Text #3

Max Range: 2.1720. Min Range: -2.1720

Max Act: 1.6821. Min Act: -0.0000

Data Index: 595392 (C4 (Web Text))

Max Activating Token Index: 10

Text #4

Max Range: 2.1720. Min Range: -2.1720

Max Act: 1.6606. Min Act: -0.0000

Data Index: 23126 (C4 (Web Text))

Max Activating Token Index: 398

Text #5

Max Range: 2.1720. Min Range: -2.1720

Max Act: 1.5003. Min Act: -0.0001

Data Index: 544824 (C4 (Web Text))

Max Activating Token Index: 835

Text #6

Max Range: 2.1720. Min Range: -2.1720

Max Act: 1.5605. Min Act: -0.0000

Data Index: 409503 (C4 (Web Text))

Max Activating Token Index: 148

Text #7

Max Range: 2.1720. Min Range: -2.1720

Max Act: 1.3268. Min Act: -0.0000

Data Index: 539220 (C4 (Web Text))

Max Activating Token Index: 342

Text #8

Max Range: 2.1720. Min Range: -2.1720

Max Act: 1.5115. Min Act: -0.0000

Data Index: 916890 (C4 (Web Text))

Max Activating Token Index: 124

Text #9

Max Range: 2.1720. Min Range: -2.1720

Max Act: 1.6114. Min Act: -0.0001

Data Index: 344061 (C4 (Web Text))

Max Activating Token Index: 109

Text #10

Max Range: 2.1720. Min Range: -2.1720

Max Act: 1.5776. Min Act: -0.0000

Data Index: 654494 (C4 (Web Text))

Max Activating Token Index: 391

Text #11

Max Range: 2.1720. Min Range: -2.1720

Max Act: 1.8789. Min Act: -0.0000

Data Index: 193585 (C4 (Web Text))

Max Activating Token Index: 321

Text #12

Max Range: 2.1720. Min Range: -2.1720

Max Act: 1.5606. Min Act: -0.0000

Data Index: 575976 (C4 (Web Text))

Max Activating Token Index: 150

Text #13

Max Range: 2.1720. Min Range: -2.1720

Max Act: 1.4192. Min Act: -0.0001

Data Index: 1263781 (C4 (Web Text))

Max Activating Token Index: 632

Text #14

Max Range: 2.1720. Min Range: -2.1720

Max Act: 1.4354. Min Act: -0.0000

Data Index: 855949 (C4 (Web Text))

Max Activating Token Index: 862

Text #15

Max Range: 2.1720. Min Range: -2.1720

Max Act: 1.4384. Min Act: -0.0000

Data Index: 595554 (C4 (Web Text))

Max Activating Token Index: 987

Text #16

Max Range: 2.1720. Min Range: -2.1720

Max Act: 1.4506. Min Act: -0.0000

Data Index: 140034 (C4 (Web Text))

Max Activating Token Index: 623

Text #17

Max Range: 2.1720. Min Range: -2.1720

Max Act: 1.4282. Min Act: -0.0000

Data Index: 1060982 (C4 (Web Text))

Max Activating Token Index: 411

Text #18

Max Range: 2.1720. Min Range: -2.1720

Max Act: 1.3930. Min Act: -0.0000

Data Index: 144037 (C4 (Web Text))

Max Activating Token Index: 995

Text #19

Max Range: 2.1720. Min Range: -2.1720

Max Act: 1.5789. Min Act: -0.0000

Data Index: 460243 (C4 (Web Text))

Max Activating Token Index: 1004