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

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

Neuron 2295 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: 0.0975. Min Range: -0.0975

Max Act: 0.0975. Min Act: -0.0000

Data Index: 1098041 (C4 (Web Text))

Max Activating Token Index: 465

Text #1

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0893. Min Act: 0.0000

Data Index: 546736 (C4 (Web Text))

Max Activating Token Index: 132

Text #2

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0832. Min Act: -0.0000

Data Index: 923439 (C4 (Web Text))

Max Activating Token Index: 358

Text #3

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0812. Min Act: -0.0000

Data Index: 897414 (C4 (Web Text))

Max Activating Token Index: 802

Text #4

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0718. Min Act: -0.0000

Data Index: 262018 (C4 (Web Text))

Max Activating Token Index: 1016

Text #5

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0726. Min Act: -0.0000

Data Index: 679283 (C4 (Web Text))

Max Activating Token Index: 214

Text #6

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0688. Min Act: -0.0000

Data Index: 367333 (C4 (Web Text))

Max Activating Token Index: 165

Text #7

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0657. Min Act: -0.0000

Data Index: 424950 (C4 (Web Text))

Max Activating Token Index: 895

Text #8

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0672. Min Act: 0.0000

Data Index: 247162 (C4 (Web Text))

Max Activating Token Index: 940

Text #9

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0716. Min Act: 0.0000

Data Index: 1193625 (C4 (Web Text))

Max Activating Token Index: 237

Text #10

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0693. Min Act: -0.0000

Data Index: 585164 (C4 (Web Text))

Max Activating Token Index: 194

Text #11

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0683. Min Act: -0.0000

Data Index: 309774 (C4 (Web Text))

Max Activating Token Index: 489

Text #12

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0654. Min Act: -0.0000

Data Index: 765593 (C4 (Web Text))

Max Activating Token Index: 99

Text #13

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0676. Min Act: -0.0000

Data Index: 782348 (C4 (Web Text))

Max Activating Token Index: 971

Text #14

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0638. Min Act: -0.0000

Data Index: 1119359 (C4 (Web Text))

Max Activating Token Index: 146

Text #15

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0635. Min Act: -0.0000

Data Index: 1346039 (C4 (Web Text))

Max Activating Token Index: 673

Text #16

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0584. Min Act: -0.0000

Data Index: 432754 (C4 (Web Text))

Max Activating Token Index: 200

Text #17

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0645. Min Act: -0.0000

Data Index: 1072326 (C4 (Web Text))

Max Activating Token Index: 211

Text #18

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0624. Min Act: -0.0000

Data Index: 449329 (C4 (Web Text))

Max Activating Token Index: 190

Text #19

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0622. Min Act: -0.0000

Data Index: 1654410 (Python Code)

Max Activating Token Index: 566