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

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

Neuron 3247 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0700. Min Act: -0.0001

Data Index: 1627378 (Python Code)

Max Activating Token Index: 632

Text #1

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0722. Min Act: -0.0001

Data Index: 1295510 (C4 (Web Text))

Max Activating Token Index: 184

Text #2

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0637. Min Act: -0.0001

Data Index: 110110 (C4 (Web Text))

Max Activating Token Index: 750

Text #3

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0673. Min Act: -0.0001

Data Index: 68295 (C4 (Web Text))

Max Activating Token Index: 178

Text #4

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0689. Min Act: -0.0001

Data Index: 531310 (C4 (Web Text))

Max Activating Token Index: 459

Text #5

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0596. Min Act: -0.0001

Data Index: 162055 (C4 (Web Text))

Max Activating Token Index: 244

Text #6

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0620. Min Act: -0.0001

Data Index: 878044 (C4 (Web Text))

Max Activating Token Index: 70

Text #7

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0603. Min Act: -0.0001

Data Index: 683164 (C4 (Web Text))

Max Activating Token Index: 889

Text #8

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0621. Min Act: -0.0001

Data Index: 62963 (C4 (Web Text))

Max Activating Token Index: 957

Text #9

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0650. Min Act: -0.0001

Data Index: 1368498 (Python Code)

Max Activating Token Index: 14

Text #10

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0636. Min Act: -0.0001

Data Index: 246723 (C4 (Web Text))

Max Activating Token Index: 239

Text #11

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0630. Min Act: -0.0001

Data Index: 1149434 (C4 (Web Text))

Max Activating Token Index: 18

Text #12

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0660. Min Act: -0.0001

Data Index: 1109467 (C4 (Web Text))

Max Activating Token Index: 992

Text #13

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0578. Min Act: -0.0001

Data Index: 768345 (C4 (Web Text))

Max Activating Token Index: 171

Text #14

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0628. Min Act: -0.0001

Data Index: 867327 (C4 (Web Text))

Max Activating Token Index: 53

Text #15

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0574. Min Act: -0.0001

Data Index: 859862 (C4 (Web Text))

Max Activating Token Index: 863

Text #16

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0616. Min Act: -0.0001

Data Index: 1148694 (C4 (Web Text))

Max Activating Token Index: 380

Text #17

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0535. Min Act: -0.0001

Data Index: 1299931 (C4 (Web Text))

Max Activating Token Index: 460

Text #18

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0606. Min Act: -0.0001

Data Index: 705542 (C4 (Web Text))

Max Activating Token Index: 310

Text #19

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0589. Min Act: -0.0001

Data Index: 1332074 (C4 (Web Text))

Max Activating Token Index: 650