Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3886 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5216. Min Range: -0.5216

Max Act: 0.5216. Min Act: -0.0000

Data Index: 1124350 (C4 (Web Text))

Max Activating Token Index: 989

Text #1

Max Range: 0.5216. Min Range: -0.5216

Max Act: 0.4962. Min Act: -0.0000

Data Index: 742350 (C4 (Web Text))

Max Activating Token Index: 980

Text #2

Max Range: 0.5216. Min Range: -0.5216

Max Act: 0.4775. Min Act: -0.0000

Data Index: 888387 (C4 (Web Text))

Max Activating Token Index: 343

Text #3

Max Range: 0.5216. Min Range: -0.5216

Max Act: 0.4525. Min Act: -0.0000

Data Index: 685705 (C4 (Web Text))

Max Activating Token Index: 631

Text #4

Max Range: 0.5216. Min Range: -0.5216

Max Act: 0.4556. Min Act: -0.0000

Data Index: 685471 (C4 (Web Text))

Max Activating Token Index: 805

Text #5

Max Range: 0.5216. Min Range: -0.5216

Max Act: 0.4512. Min Act: -0.0000

Data Index: 17496 (C4 (Web Text))

Max Activating Token Index: 624

Text #6

Max Range: 0.5216. Min Range: -0.5216

Max Act: 0.4658. Min Act: -0.0001

Data Index: 874689 (C4 (Web Text))

Max Activating Token Index: 88

Text #7

Max Range: 0.5216. Min Range: -0.5216

Max Act: 0.4423. Min Act: -0.0001

Data Index: 730696 (C4 (Web Text))

Max Activating Token Index: 546

Text #8

Max Range: 0.5216. Min Range: -0.5216

Max Act: 0.4381. Min Act: -0.0000

Data Index: 830599 (C4 (Web Text))

Max Activating Token Index: 360

Text #9

Max Range: 0.5216. Min Range: -0.5216

Max Act: 0.4250. Min Act: -0.0000

Data Index: 1027801 (C4 (Web Text))

Max Activating Token Index: 943

Text #10

Max Range: 0.5216. Min Range: -0.5216

Max Act: 0.4232. Min Act: -0.0000

Data Index: 448914 (C4 (Web Text))

Max Activating Token Index: 325

Text #11

Max Range: 0.5216. Min Range: -0.5216

Max Act: 0.4170. Min Act: -0.0001

Data Index: 695373 (C4 (Web Text))

Max Activating Token Index: 504

Text #12

Max Range: 0.5216. Min Range: -0.5216

Max Act: 0.4457. Min Act: -0.0000

Data Index: 1187236 (C4 (Web Text))

Max Activating Token Index: 674

Text #13

Max Range: 0.5216. Min Range: -0.5216

Max Act: 0.4284. Min Act: -0.0000

Data Index: 772370 (C4 (Web Text))

Max Activating Token Index: 516

Text #14

Max Range: 0.5216. Min Range: -0.5216

Max Act: 0.4154. Min Act: -0.0000

Data Index: 225596 (C4 (Web Text))

Max Activating Token Index: 620

Text #15

Max Range: 0.5216. Min Range: -0.5216

Max Act: 0.4241. Min Act: -0.0000

Data Index: 594857 (C4 (Web Text))

Max Activating Token Index: 457

Text #16

Max Range: 0.5216. Min Range: -0.5216

Max Act: 0.4075. Min Act: -0.0001

Data Index: 739675 (C4 (Web Text))

Max Activating Token Index: 1002

Text #17

Max Range: 0.5216. Min Range: -0.5216

Max Act: 0.4175. Min Act: -0.0000

Data Index: 347825 (C4 (Web Text))

Max Activating Token Index: 391

Text #18

Max Range: 0.5216. Min Range: -0.5216

Max Act: 0.4020. Min Act: -0.0000

Data Index: 632135 (C4 (Web Text))

Max Activating Token Index: 609

Text #19

Max Range: 0.5216. Min Range: -0.5216

Max Act: 0.4128. Min Act: -0.0000

Data Index: 484287 (C4 (Web Text))

Max Activating Token Index: 176