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

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

Neuron 6114 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: 3.3047. Min Range: -3.3047

Max Act: 3.3047. Min Act: -0.0000

Data Index: 193708 (C4 (Web Text))

Max Activating Token Index: 507

Text #1

Max Range: 3.3047. Min Range: -3.3047

Max Act: 3.0056. Min Act: -0.0000

Data Index: 1310299 (C4 (Web Text))

Max Activating Token Index: 739

Text #2

Max Range: 3.3047. Min Range: -3.3047

Max Act: 2.8373. Min Act: -0.0000

Data Index: 87755 (C4 (Web Text))

Max Activating Token Index: 155

Text #3

Max Range: 3.3047. Min Range: -3.3047

Max Act: 2.8460. Min Act: -0.0000

Data Index: 221397 (C4 (Web Text))

Max Activating Token Index: 601

Text #4

Max Range: 3.3047. Min Range: -3.3047

Max Act: 3.0187. Min Act: -0.0000

Data Index: 833306 (C4 (Web Text))

Max Activating Token Index: 284

Text #5

Max Range: 3.3047. Min Range: -3.3047

Max Act: 2.7126. Min Act: -0.0000

Data Index: 156012 (C4 (Web Text))

Max Activating Token Index: 899

Text #6

Max Range: 3.3047. Min Range: -3.3047

Max Act: 2.6302. Min Act: -0.0000

Data Index: 1173124 (C4 (Web Text))

Max Activating Token Index: 971

Text #7

Max Range: 3.3047. Min Range: -3.3047

Max Act: 2.2435. Min Act: -0.0000

Data Index: 1183942 (C4 (Web Text))

Max Activating Token Index: 838

Text #8

Max Range: 3.3047. Min Range: -3.3047

Max Act: 2.5872. Min Act: -0.0000

Data Index: 1029639 (C4 (Web Text))

Max Activating Token Index: 821

Text #9

Max Range: 3.3047. Min Range: -3.3047

Max Act: 2.3575. Min Act: -0.0000

Data Index: 761548 (C4 (Web Text))

Max Activating Token Index: 869

Text #10

Max Range: 3.3047. Min Range: -3.3047

Max Act: 2.4082. Min Act: -0.0000

Data Index: 884560 (C4 (Web Text))

Max Activating Token Index: 55

Text #11

Max Range: 3.3047. Min Range: -3.3047

Max Act: 2.3564. Min Act: -0.0000

Data Index: 58559 (C4 (Web Text))

Max Activating Token Index: 557

Text #12

Max Range: 3.3047. Min Range: -3.3047

Max Act: 2.2394. Min Act: -0.0000

Data Index: 1332890 (C4 (Web Text))

Max Activating Token Index: 180

Text #13

Max Range: 3.3047. Min Range: -3.3047

Max Act: 2.3549. Min Act: -0.0000

Data Index: 414369 (C4 (Web Text))

Max Activating Token Index: 111

Text #14

Max Range: 3.3047. Min Range: -3.3047

Max Act: 2.4562. Min Act: -0.0000

Data Index: 408483 (C4 (Web Text))

Max Activating Token Index: 401

Text #15

Max Range: 3.3047. Min Range: -3.3047

Max Act: 2.2019. Min Act: -0.0000

Data Index: 500759 (C4 (Web Text))

Max Activating Token Index: 969

Text #16

Max Range: 3.3047. Min Range: -3.3047

Max Act: 2.1735. Min Act: -0.0000

Data Index: 228023 (C4 (Web Text))

Max Activating Token Index: 915

Text #17

Max Range: 3.3047. Min Range: -3.3047

Max Act: 2.1702. Min Act: -0.0000

Data Index: 942130 (C4 (Web Text))

Max Activating Token Index: 237

Text #18

Max Range: 3.3047. Min Range: -3.3047

Max Act: 2.3650. Min Act: -0.0000

Data Index: 994401 (C4 (Web Text))

Max Activating Token Index: 1002

Text #19

Max Range: 3.3047. Min Range: -3.3047

Max Act: 2.2337. Min Act: -0.0000

Data Index: 618612 (C4 (Web Text))

Max Activating Token Index: 150