Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 412 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5198. Min Range: -0.5198

Max Act: 0.5198. Min Act: -0.0000

Data Index: 1046903 (C4 (Web Text))

Max Activating Token Index: 319

Text #1

Max Range: 0.5198. Min Range: -0.5198

Max Act: 0.4708. Min Act: -0.0000

Data Index: 345416 (C4 (Web Text))

Max Activating Token Index: 148

Text #2

Max Range: 0.5198. Min Range: -0.5198

Max Act: 0.4599. Min Act: -0.0000

Data Index: 27643 (C4 (Web Text))

Max Activating Token Index: 92

Text #3

Max Range: 0.5198. Min Range: -0.5198

Max Act: 0.4440. Min Act: -0.0000

Data Index: 646699 (C4 (Web Text))

Max Activating Token Index: 428

Text #4

Max Range: 0.5198. Min Range: -0.5198

Max Act: 0.4732. Min Act: -0.0000

Data Index: 837433 (C4 (Web Text))

Max Activating Token Index: 308

Text #5

Max Range: 0.5198. Min Range: -0.5198

Max Act: 0.4383. Min Act: -0.0000

Data Index: 995043 (C4 (Web Text))

Max Activating Token Index: 50

Text #6

Max Range: 0.5198. Min Range: -0.5198

Max Act: 0.4410. Min Act: -0.0000

Data Index: 852479 (C4 (Web Text))

Max Activating Token Index: 560

Text #7

Max Range: 0.5198. Min Range: -0.5198

Max Act: 0.4195. Min Act: -0.0000

Data Index: 676785 (C4 (Web Text))

Max Activating Token Index: 51

Text #8

Max Range: 0.5198. Min Range: -0.5198

Max Act: 0.4338. Min Act: -0.0000

Data Index: 667228 (C4 (Web Text))

Max Activating Token Index: 993

Text #9

Max Range: 0.5198. Min Range: -0.5198

Max Act: 0.4266. Min Act: -0.0000

Data Index: 273450 (C4 (Web Text))

Max Activating Token Index: 688

Text #10

Max Range: 0.5198. Min Range: -0.5198

Max Act: 0.4131. Min Act: -0.0000

Data Index: 1448841 (Python Code)

Max Activating Token Index: 594

Text #11

Max Range: 0.5198. Min Range: -0.5198

Max Act: 0.4142. Min Act: -0.0000

Data Index: 614957 (C4 (Web Text))

Max Activating Token Index: 973

Text #12

Max Range: 0.5198. Min Range: -0.5198

Max Act: 0.4264. Min Act: -0.0000

Data Index: 475239 (C4 (Web Text))

Max Activating Token Index: 157

Text #13

Max Range: 0.5198. Min Range: -0.5198

Max Act: 0.3948. Min Act: -0.0000

Data Index: 421527 (C4 (Web Text))

Max Activating Token Index: 109

Text #14

Max Range: 0.5198. Min Range: -0.5198

Max Act: 0.3968. Min Act: -0.0000

Data Index: 607205 (C4 (Web Text))

Max Activating Token Index: 854

Text #15

Max Range: 0.5198. Min Range: -0.5198

Max Act: 0.3826. Min Act: -0.0000

Data Index: 1283081 (C4 (Web Text))

Max Activating Token Index: 967

Text #16

Max Range: 0.5198. Min Range: -0.5198

Max Act: 0.3746. Min Act: -0.0000

Data Index: 354286 (C4 (Web Text))

Max Activating Token Index: 289

Text #17

Max Range: 0.5198. Min Range: -0.5198

Max Act: 0.3736. Min Act: -0.0000

Data Index: 1425989 (Python Code)

Max Activating Token Index: 917

Text #18

Max Range: 0.5198. Min Range: -0.5198

Max Act: 0.3929. Min Act: -0.0000

Data Index: 1370111 (Python Code)

Max Activating Token Index: 249

Text #19

Max Range: 0.5198. Min Range: -0.5198

Max Act: 0.3633. Min Act: -0.0000

Data Index: 1530812 (Python Code)

Max Activating Token Index: 290