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

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

Neuron 827 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3170. Min Range: -2.3170

Max Act: 2.3170. Min Act: -0.0000

Data Index: 216490 (C4 (Web Text))

Max Activating Token Index: 169

Text #1

Max Range: 2.3170. Min Range: -2.3170

Max Act: 1.9977. Min Act: -0.0000

Data Index: 148183 (C4 (Web Text))

Max Activating Token Index: 420

Text #2

Max Range: 2.3170. Min Range: -2.3170

Max Act: 1.7395. Min Act: -0.0000

Data Index: 1323721 (C4 (Web Text))

Max Activating Token Index: 309

Text #3

Max Range: 2.3170. Min Range: -2.3170

Max Act: 1.7199. Min Act: -0.0000

Data Index: 1030500 (C4 (Web Text))

Max Activating Token Index: 812

Text #4

Max Range: 2.3170. Min Range: -2.3170

Max Act: 1.6808. Min Act: -0.0000

Data Index: 981185 (C4 (Web Text))

Max Activating Token Index: 254

Text #5

Max Range: 2.3170. Min Range: -2.3170

Max Act: 1.5805. Min Act: -0.0000

Data Index: 831961 (C4 (Web Text))

Max Activating Token Index: 932

Text #6

Max Range: 2.3170. Min Range: -2.3170

Max Act: 1.6317. Min Act: -0.0000

Data Index: 1276947 (C4 (Web Text))

Max Activating Token Index: 40

Text #7

Max Range: 2.3170. Min Range: -2.3170

Max Act: 1.6281. Min Act: -0.0000

Data Index: 564432 (C4 (Web Text))

Max Activating Token Index: 362

Text #8

Max Range: 2.3170. Min Range: -2.3170

Max Act: 1.4907. Min Act: -0.0000

Data Index: 301863 (C4 (Web Text))

Max Activating Token Index: 505

Text #9

Max Range: 2.3170. Min Range: -2.3170

Max Act: 1.5707. Min Act: -0.0000

Data Index: 515362 (C4 (Web Text))

Max Activating Token Index: 633

Text #10

Max Range: 2.3170. Min Range: -2.3170

Max Act: 1.5215. Min Act: -0.0000

Data Index: 645370 (C4 (Web Text))

Max Activating Token Index: 595

Text #11

Max Range: 2.3170. Min Range: -2.3170

Max Act: 1.5192. Min Act: -0.0000

Data Index: 352499 (C4 (Web Text))

Max Activating Token Index: 759

Text #12

Max Range: 2.3170. Min Range: -2.3170

Max Act: 1.4138. Min Act: -0.0000

Data Index: 550786 (C4 (Web Text))

Max Activating Token Index: 262

Text #13

Max Range: 2.3170. Min Range: -2.3170

Max Act: 1.5725. Min Act: -0.0000

Data Index: 265955 (C4 (Web Text))

Max Activating Token Index: 143

Text #14

Max Range: 2.3170. Min Range: -2.3170

Max Act: 1.4727. Min Act: -0.0000

Data Index: 983114 (C4 (Web Text))

Max Activating Token Index: 42

Text #15

Max Range: 2.3170. Min Range: -2.3170

Max Act: 1.3688. Min Act: -0.0000

Data Index: 1063030 (C4 (Web Text))

Max Activating Token Index: 378

Text #16

Max Range: 2.3170. Min Range: -2.3170

Max Act: 1.4419. Min Act: -0.0000

Data Index: 465321 (C4 (Web Text))

Max Activating Token Index: 255

Text #17

Max Range: 2.3170. Min Range: -2.3170

Max Act: 1.3516. Min Act: -0.0000

Data Index: 797828 (C4 (Web Text))

Max Activating Token Index: 234

Text #18

Max Range: 2.3170. Min Range: -2.3170

Max Act: 1.4633. Min Act: -0.0000

Data Index: 616180 (C4 (Web Text))

Max Activating Token Index: 78

Text #19

Max Range: 2.3170. Min Range: -2.3170

Max Act: 1.3109. Min Act: -0.0000

Data Index: 1133467 (C4 (Web Text))

Max Activating Token Index: 235