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

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

Neuron 4064 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: 2.3238. Min Range: -2.3238

Max Act: 2.3238. Min Act: -0.0000

Data Index: 591940 (C4 (Web Text))

Max Activating Token Index: 40

Text #1

Max Range: 2.3238. Min Range: -2.3238

Max Act: 2.1798. Min Act: -0.0000

Data Index: 787539 (C4 (Web Text))

Max Activating Token Index: 204

Text #2

Max Range: 2.3238. Min Range: -2.3238

Max Act: 1.9007. Min Act: -0.0000

Data Index: 98427 (C4 (Web Text))

Max Activating Token Index: 200

Text #3

Max Range: 2.3238. Min Range: -2.3238

Max Act: 2.0112. Min Act: -0.0000

Data Index: 29104 (C4 (Web Text))

Max Activating Token Index: 486

Text #4

Max Range: 2.3238. Min Range: -2.3238

Max Act: 2.0812. Min Act: -0.0000

Data Index: 1116130 (C4 (Web Text))

Max Activating Token Index: 40

Text #5

Max Range: 2.3238. Min Range: -2.3238

Max Act: 1.7495. Min Act: -0.0000

Data Index: 110282 (C4 (Web Text))

Max Activating Token Index: 716

Text #6

Max Range: 2.3238. Min Range: -2.3238

Max Act: 1.8037. Min Act: -0.0000

Data Index: 1013450 (C4 (Web Text))

Max Activating Token Index: 419

Text #7

Max Range: 2.3238. Min Range: -2.3238

Max Act: 1.8697. Min Act: -0.0000

Data Index: 1269747 (C4 (Web Text))

Max Activating Token Index: 202

Text #8

Max Range: 2.3238. Min Range: -2.3238

Max Act: 1.7166. Min Act: -0.0000

Data Index: 1090389 (C4 (Web Text))

Max Activating Token Index: 905

Text #9

Max Range: 2.3238. Min Range: -2.3238

Max Act: 1.6594. Min Act: -0.0000

Data Index: 1052401 (C4 (Web Text))

Max Activating Token Index: 101

Text #10

Max Range: 2.3238. Min Range: -2.3238

Max Act: 1.6961. Min Act: -0.0000

Data Index: 137394 (C4 (Web Text))

Max Activating Token Index: 784

Text #11

Max Range: 2.3238. Min Range: -2.3238

Max Act: 1.6291. Min Act: -0.0000

Data Index: 708215 (C4 (Web Text))

Max Activating Token Index: 9

Text #12

Max Range: 2.3238. Min Range: -2.3238

Max Act: 1.6740. Min Act: -0.0001

Data Index: 1223562 (C4 (Web Text))

Max Activating Token Index: 582

Text #13

Max Range: 2.3238. Min Range: -2.3238

Max Act: 1.5852. Min Act: -0.0000

Data Index: 969537 (C4 (Web Text))

Max Activating Token Index: 254

Text #14

Max Range: 2.3238. Min Range: -2.3238

Max Act: 1.6057. Min Act: -0.0000

Data Index: 304096 (C4 (Web Text))

Max Activating Token Index: 24

Text #15

Max Range: 2.3238. Min Range: -2.3238

Max Act: 1.6451. Min Act: -0.0000

Data Index: 1221684 (C4 (Web Text))

Max Activating Token Index: 513

Text #16

Max Range: 2.3238. Min Range: -2.3238

Max Act: 1.7746. Min Act: -0.0000

Data Index: 583612 (C4 (Web Text))

Max Activating Token Index: 324

Text #17

Max Range: 2.3238. Min Range: -2.3238

Max Act: 1.6409. Min Act: -0.0000

Data Index: 291526 (C4 (Web Text))

Max Activating Token Index: 42

Text #18

Max Range: 2.3238. Min Range: -2.3238

Max Act: 1.6290. Min Act: -0.0000

Data Index: 1017524 (C4 (Web Text))

Max Activating Token Index: 463

Text #19

Max Range: 2.3238. Min Range: -2.3238

Max Act: 1.6327. Min Act: -0.0000

Data Index: 1015000 (C4 (Web Text))

Max Activating Token Index: 538