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

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

Neuron 1378 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5244. Min Range: -0.5244

Max Act: 0.5244. Min Act: -0.0000

Data Index: 874080 (C4 (Web Text))

Max Activating Token Index: 319

Text #1

Max Range: 0.5244. Min Range: -0.5244

Max Act: 0.4562. Min Act: -0.0000

Data Index: 303806 (C4 (Web Text))

Max Activating Token Index: 184

Text #2

Max Range: 0.5244. Min Range: -0.5244

Max Act: 0.4801. Min Act: -0.0000

Data Index: 307528 (C4 (Web Text))

Max Activating Token Index: 506

Text #3

Max Range: 0.5244. Min Range: -0.5244

Max Act: 0.4751. Min Act: -0.0000

Data Index: 1279677 (C4 (Web Text))

Max Activating Token Index: 449

Text #4

Max Range: 0.5244. Min Range: -0.5244

Max Act: 0.4711. Min Act: -0.0000

Data Index: 717979 (C4 (Web Text))

Max Activating Token Index: 699

Text #5

Max Range: 0.5244. Min Range: -0.5244

Max Act: 0.4104. Min Act: -0.0000

Data Index: 492703 (C4 (Web Text))

Max Activating Token Index: 744

Text #6

Max Range: 0.5244. Min Range: -0.5244

Max Act: 0.4515. Min Act: -0.0000

Data Index: 937620 (C4 (Web Text))

Max Activating Token Index: 409

Text #7

Max Range: 0.5244. Min Range: -0.5244

Max Act: 0.4129. Min Act: -0.0000

Data Index: 1038504 (C4 (Web Text))

Max Activating Token Index: 707

Text #8

Max Range: 0.5244. Min Range: -0.5244

Max Act: 0.4265. Min Act: -0.0000

Data Index: 333338 (C4 (Web Text))

Max Activating Token Index: 218

Text #9

Max Range: 0.5244. Min Range: -0.5244

Max Act: 0.4251. Min Act: -0.0000

Data Index: 242848 (C4 (Web Text))

Max Activating Token Index: 803

Text #10

Max Range: 0.5244. Min Range: -0.5244

Max Act: 0.4225. Min Act: -0.0000

Data Index: 457518 (C4 (Web Text))

Max Activating Token Index: 978

Text #11

Max Range: 0.5244. Min Range: -0.5244

Max Act: 0.4175. Min Act: -0.0000

Data Index: 1031879 (C4 (Web Text))

Max Activating Token Index: 408

Text #12

Max Range: 0.5244. Min Range: -0.5244

Max Act: 0.4280. Min Act: -0.0000

Data Index: 836410 (C4 (Web Text))

Max Activating Token Index: 99

Text #13

Max Range: 0.5244. Min Range: -0.5244

Max Act: 0.4240. Min Act: -0.0000

Data Index: 132851 (C4 (Web Text))

Max Activating Token Index: 463

Text #14

Max Range: 0.5244. Min Range: -0.5244

Max Act: 0.4031. Min Act: -0.0000

Data Index: 103715 (C4 (Web Text))

Max Activating Token Index: 542

Text #15

Max Range: 0.5244. Min Range: -0.5244

Max Act: 0.4428. Min Act: -0.0000

Data Index: 362293 (C4 (Web Text))

Max Activating Token Index: 416

Text #16

Max Range: 0.5244. Min Range: -0.5244

Max Act: 0.4408. Min Act: -0.0000

Data Index: 696987 (C4 (Web Text))

Max Activating Token Index: 713

Text #17

Max Range: 0.5244. Min Range: -0.5244

Max Act: 0.4247. Min Act: -0.0000

Data Index: 353029 (C4 (Web Text))

Max Activating Token Index: 416

Text #18

Max Range: 0.5244. Min Range: -0.5244

Max Act: 0.4259. Min Act: -0.0000

Data Index: 593260 (C4 (Web Text))

Max Activating Token Index: 130

Text #19

Max Range: 0.5244. Min Range: -0.5244

Max Act: 0.4171. Min Act: -0.0000

Data Index: 240798 (C4 (Web Text))

Max Activating Token Index: 630