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

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

Neuron 1298 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.8557. Min Range: -0.8557

Max Act: 0.8557. Min Act: -0.0000

Data Index: 1307647 (C4 (Web Text))

Max Activating Token Index: 660

Text #1

Max Range: 0.8557. Min Range: -0.8557

Max Act: 0.7548. Min Act: -0.0000

Data Index: 293209 (C4 (Web Text))

Max Activating Token Index: 956

Text #2

Max Range: 0.8557. Min Range: -0.8557

Max Act: 0.7175. Min Act: -0.0000

Data Index: 300290 (C4 (Web Text))

Max Activating Token Index: 317

Text #3

Max Range: 0.8557. Min Range: -0.8557

Max Act: 0.7614. Min Act: -0.0000

Data Index: 369958 (C4 (Web Text))

Max Activating Token Index: 791

Text #4

Max Range: 0.8557. Min Range: -0.8557

Max Act: 0.6851. Min Act: -0.0000

Data Index: 397000 (C4 (Web Text))

Max Activating Token Index: 691

Text #5

Max Range: 0.8557. Min Range: -0.8557

Max Act: 0.6189. Min Act: -0.0000

Data Index: 86556 (C4 (Web Text))

Max Activating Token Index: 592

Text #6

Max Range: 0.8557. Min Range: -0.8557

Max Act: 0.6010. Min Act: 0.0000

Data Index: 1197868 (C4 (Web Text))

Max Activating Token Index: 84

Text #7

Max Range: 0.8557. Min Range: -0.8557

Max Act: 0.5953. Min Act: -0.0000

Data Index: 495292 (C4 (Web Text))

Max Activating Token Index: 225

Text #8

Max Range: 0.8557. Min Range: -0.8557

Max Act: 0.5705. Min Act: -0.0000

Data Index: 526032 (C4 (Web Text))

Max Activating Token Index: 410

Text #9

Max Range: 0.8557. Min Range: -0.8557

Max Act: 0.5844. Min Act: -0.0000

Data Index: 843606 (C4 (Web Text))

Max Activating Token Index: 625

Text #10

Max Range: 0.8557. Min Range: -0.8557

Max Act: 0.5617. Min Act: -0.0000

Data Index: 289212 (C4 (Web Text))

Max Activating Token Index: 480

Text #11

Max Range: 0.8557. Min Range: -0.8557

Max Act: 0.5584. Min Act: -0.0000

Data Index: 873443 (C4 (Web Text))

Max Activating Token Index: 731

Text #12

Max Range: 0.8557. Min Range: -0.8557

Max Act: 0.5386. Min Act: -0.0000

Data Index: 314246 (C4 (Web Text))

Max Activating Token Index: 573

Text #13

Max Range: 0.8557. Min Range: -0.8557

Max Act: 0.5628. Min Act: -0.0000

Data Index: 287688 (C4 (Web Text))

Max Activating Token Index: 742

Text #14

Max Range: 0.8557. Min Range: -0.8557

Max Act: 0.5525. Min Act: 0.0001

Data Index: 982520 (C4 (Web Text))

Max Activating Token Index: 263

Text #15

Max Range: 0.8557. Min Range: -0.8557

Max Act: 0.5450. Min Act: -0.0000

Data Index: 872318 (C4 (Web Text))

Max Activating Token Index: 341

Text #16

Max Range: 0.8557. Min Range: -0.8557

Max Act: 0.5233. Min Act: -0.0000

Data Index: 1036671 (C4 (Web Text))

Max Activating Token Index: 140

Text #17

Max Range: 0.8557. Min Range: -0.8557

Max Act: 0.5465. Min Act: -0.0000

Data Index: 188456 (C4 (Web Text))

Max Activating Token Index: 113

Text #18

Max Range: 0.8557. Min Range: -0.8557

Max Act: 0.5274. Min Act: -0.0000

Data Index: 650633 (C4 (Web Text))

Max Activating Token Index: 637

Text #19

Max Range: 0.8557. Min Range: -0.8557

Max Act: 0.5234. Min Act: -0.0000

Data Index: 1263765 (C4 (Web Text))

Max Activating Token Index: 29