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

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

Neuron 3269 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6294. Min Range: -2.6294

Max Act: 2.6294. Min Act: -0.0000

Data Index: 787105 (C4 (Web Text))

Max Activating Token Index: 445

Text #1

Max Range: 2.6294. Min Range: -2.6294

Max Act: 2.3981. Min Act: -0.0000

Data Index: 5057 (C4 (Web Text))

Max Activating Token Index: 152

Text #2

Max Range: 2.6294. Min Range: -2.6294

Max Act: 2.3694. Min Act: -0.0000

Data Index: 953166 (C4 (Web Text))

Max Activating Token Index: 383

Text #3

Max Range: 2.6294. Min Range: -2.6294

Max Act: 2.3294. Min Act: -0.0000

Data Index: 643086 (C4 (Web Text))

Max Activating Token Index: 65

Text #4

Max Range: 2.6294. Min Range: -2.6294

Max Act: 2.5617. Min Act: -0.0000

Data Index: 379132 (C4 (Web Text))

Max Activating Token Index: 473

Text #5

Max Range: 2.6294. Min Range: -2.6294

Max Act: 2.2380. Min Act: -0.0000

Data Index: 1106594 (C4 (Web Text))

Max Activating Token Index: 41

Text #6

Max Range: 2.6294. Min Range: -2.6294

Max Act: 2.3156. Min Act: -0.0000

Data Index: 567040 (C4 (Web Text))

Max Activating Token Index: 804

Text #7

Max Range: 2.6294. Min Range: -2.6294

Max Act: 2.3387. Min Act: -0.0000

Data Index: 355031 (C4 (Web Text))

Max Activating Token Index: 228

Text #8

Max Range: 2.6294. Min Range: -2.6294

Max Act: 2.4532. Min Act: -0.0000

Data Index: 144565 (C4 (Web Text))

Max Activating Token Index: 859

Text #9

Max Range: 2.6294. Min Range: -2.6294

Max Act: 2.2322. Min Act: -0.0000

Data Index: 374189 (C4 (Web Text))

Max Activating Token Index: 504

Text #10

Max Range: 2.6294. Min Range: -2.6294

Max Act: 2.0006. Min Act: -0.0000

Data Index: 1262188 (C4 (Web Text))

Max Activating Token Index: 432

Text #11

Max Range: 2.6294. Min Range: -2.6294

Max Act: 1.9551. Min Act: -0.0000

Data Index: 109349 (C4 (Web Text))

Max Activating Token Index: 210

Text #12

Max Range: 2.6294. Min Range: -2.6294

Max Act: 1.9829. Min Act: -0.0000

Data Index: 836578 (C4 (Web Text))

Max Activating Token Index: 97

Text #13

Max Range: 2.6294. Min Range: -2.6294

Max Act: 1.8951. Min Act: -0.0000

Data Index: 210676 (C4 (Web Text))

Max Activating Token Index: 612

Text #14

Max Range: 2.6294. Min Range: -2.6294

Max Act: 1.7609. Min Act: -0.0000

Data Index: 352227 (C4 (Web Text))

Max Activating Token Index: 367

Text #15

Max Range: 2.6294. Min Range: -2.6294

Max Act: 1.9012. Min Act: -0.0000

Data Index: 258287 (C4 (Web Text))

Max Activating Token Index: 616

Text #16

Max Range: 2.6294. Min Range: -2.6294

Max Act: 2.1083. Min Act: -0.0000

Data Index: 324917 (C4 (Web Text))

Max Activating Token Index: 573

Text #17

Max Range: 2.6294. Min Range: -2.6294

Max Act: 1.9604. Min Act: -0.0000

Data Index: 666634 (C4 (Web Text))

Max Activating Token Index: 893

Text #18

Max Range: 2.6294. Min Range: -2.6294

Max Act: 1.8683. Min Act: -0.0000

Data Index: 1001478 (C4 (Web Text))

Max Activating Token Index: 69

Text #19

Max Range: 2.6294. Min Range: -2.6294

Max Act: 1.8635. Min Act: -0.0000

Data Index: 1135464 (C4 (Web Text))

Max Activating Token Index: 257