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

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

Neuron 194 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0977. Min Act: -0.0002

Data Index: 1119428 (C4 (Web Text))

Max Activating Token Index: 417

Text #1

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0779. Min Act: -0.0002

Data Index: 773023 (C4 (Web Text))

Max Activating Token Index: 243

Text #2

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0802. Min Act: -0.0002

Data Index: 719234 (C4 (Web Text))

Max Activating Token Index: 280

Text #3

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0770. Min Act: -0.0002

Data Index: 1214129 (C4 (Web Text))

Max Activating Token Index: 1004

Text #4

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0730. Min Act: -0.0002

Data Index: 871879 (C4 (Web Text))

Max Activating Token Index: 150

Text #5

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0709. Min Act: -0.0002

Data Index: 1195643 (C4 (Web Text))

Max Activating Token Index: 71

Text #6

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0705. Min Act: -0.0002

Data Index: 1186790 (C4 (Web Text))

Max Activating Token Index: 944

Text #7

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0701. Min Act: -0.0002

Data Index: 754205 (C4 (Web Text))

Max Activating Token Index: 282

Text #8

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0700. Min Act: -0.0002

Data Index: 945684 (C4 (Web Text))

Max Activating Token Index: 855

Text #9

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0681. Min Act: -0.0002

Data Index: 189743 (C4 (Web Text))

Max Activating Token Index: 375

Text #10

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0673. Min Act: -0.0002

Data Index: 741408 (C4 (Web Text))

Max Activating Token Index: 826

Text #11

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0659. Min Act: -0.0002

Data Index: 948359 (C4 (Web Text))

Max Activating Token Index: 286

Text #12

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0651. Min Act: -0.0002

Data Index: 696778 (C4 (Web Text))

Max Activating Token Index: 809

Text #13

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0647. Min Act: -0.0002

Data Index: 757607 (C4 (Web Text))

Max Activating Token Index: 44

Text #14

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0666. Min Act: -0.0002

Data Index: 488837 (C4 (Web Text))

Max Activating Token Index: 213

Text #15

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0639. Min Act: -0.0002

Data Index: 1208614 (C4 (Web Text))

Max Activating Token Index: 119

Text #16

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0655. Min Act: -0.0002

Data Index: 247397 (C4 (Web Text))

Max Activating Token Index: 73

Text #17

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0623. Min Act: -0.0002

Data Index: 235328 (C4 (Web Text))

Max Activating Token Index: 899

Text #18

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0598. Min Act: -0.0002

Data Index: 326151 (C4 (Web Text))

Max Activating Token Index: 604

Text #19

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0608. Min Act: -0.0002

Data Index: 40714 (C4 (Web Text))

Max Activating Token Index: 489