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

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

Neuron 986 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: 2.7136. Min Range: -2.7136

Max Act: 2.7136. Min Act: -0.0000

Data Index: 226522 (C4 (Web Text))

Max Activating Token Index: 120

Text #1

Max Range: 2.7136. Min Range: -2.7136

Max Act: 2.1204. Min Act: -0.0000

Data Index: 496086 (C4 (Web Text))

Max Activating Token Index: 595

Text #2

Max Range: 2.7136. Min Range: -2.7136

Max Act: 2.1615. Min Act: 0.0000

Data Index: 595223 (C4 (Web Text))

Max Activating Token Index: 252

Text #3

Max Range: 2.7136. Min Range: -2.7136

Max Act: 2.1883. Min Act: -0.0000

Data Index: 221016 (C4 (Web Text))

Max Activating Token Index: 1018

Text #4

Max Range: 2.7136. Min Range: -2.7136

Max Act: 2.1455. Min Act: -0.0000

Data Index: 17348 (C4 (Web Text))

Max Activating Token Index: 316

Text #5

Max Range: 2.7136. Min Range: -2.7136

Max Act: 1.9528. Min Act: -0.0000

Data Index: 712461 (C4 (Web Text))

Max Activating Token Index: 477

Text #6

Max Range: 2.7136. Min Range: -2.7136

Max Act: 1.9235. Min Act: -0.0000

Data Index: 913771 (C4 (Web Text))

Max Activating Token Index: 451

Text #7

Max Range: 2.7136. Min Range: -2.7136

Max Act: 1.7457. Min Act: -0.0000

Data Index: 325735 (C4 (Web Text))

Max Activating Token Index: 516

Text #8

Max Range: 2.7136. Min Range: -2.7136

Max Act: 1.7104. Min Act: -0.0000

Data Index: 551218 (C4 (Web Text))

Max Activating Token Index: 155

Text #9

Max Range: 2.7136. Min Range: -2.7136

Max Act: 1.6102. Min Act: -0.0000

Data Index: 310039 (C4 (Web Text))

Max Activating Token Index: 772

Text #10

Max Range: 2.7136. Min Range: -2.7136

Max Act: 1.6194. Min Act: -0.0000

Data Index: 411647 (C4 (Web Text))

Max Activating Token Index: 197

Text #11

Max Range: 2.7136. Min Range: -2.7136

Max Act: 1.4694. Min Act: -0.0000

Data Index: 354461 (C4 (Web Text))

Max Activating Token Index: 612

Text #12

Max Range: 2.7136. Min Range: -2.7136

Max Act: 1.5581. Min Act: -0.0000

Data Index: 222058 (C4 (Web Text))

Max Activating Token Index: 347

Text #13

Max Range: 2.7136. Min Range: -2.7136

Max Act: 1.5423. Min Act: -0.0000

Data Index: 492698 (C4 (Web Text))

Max Activating Token Index: 248

Text #14

Max Range: 2.7136. Min Range: -2.7136

Max Act: 1.5615. Min Act: -0.0000

Data Index: 679554 (C4 (Web Text))

Max Activating Token Index: 854

Text #15

Max Range: 2.7136. Min Range: -2.7136

Max Act: 1.4058. Min Act: 0.0001

Data Index: 1085716 (C4 (Web Text))

Max Activating Token Index: 215

Text #16

Max Range: 2.7136. Min Range: -2.7136

Max Act: 1.4451. Min Act: -0.0000

Data Index: 204650 (C4 (Web Text))

Max Activating Token Index: 548

Text #17

Max Range: 2.7136. Min Range: -2.7136

Max Act: 1.4693. Min Act: -0.0000

Data Index: 121114 (C4 (Web Text))

Max Activating Token Index: 1009

Text #18

Max Range: 2.7136. Min Range: -2.7136

Max Act: 1.4480. Min Act: -0.0000

Data Index: 453261 (C4 (Web Text))

Max Activating Token Index: 949

Text #19

Max Range: 2.7136. Min Range: -2.7136

Max Act: 1.4350. Min Act: 0.0000

Data Index: 665470 (C4 (Web Text))

Max Activating Token Index: 714