Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3829 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0806. Min Act: -0.0002

Data Index: 235520 (C4 (Web Text))

Max Activating Token Index: 787

Text #1

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0645. Min Act: -0.0002

Data Index: 377485 (C4 (Web Text))

Max Activating Token Index: 928

Text #2

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0603. Min Act: -0.0002

Data Index: 956469 (C4 (Web Text))

Max Activating Token Index: 783

Text #3

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0606. Min Act: -0.0002

Data Index: 1295285 (C4 (Web Text))

Max Activating Token Index: 687

Text #4

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0559. Min Act: -0.0002

Data Index: 1262550 (C4 (Web Text))

Max Activating Token Index: 257

Text #5

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0556. Min Act: -0.0002

Data Index: 769715 (C4 (Web Text))

Max Activating Token Index: 418

Text #6

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0590. Min Act: -0.0002

Data Index: 171271 (C4 (Web Text))

Max Activating Token Index: 17

Text #7

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0574. Min Act: -0.0002

Data Index: 1137132 (C4 (Web Text))

Max Activating Token Index: 792

Text #8

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0537. Min Act: -0.0002

Data Index: 107645 (C4 (Web Text))

Max Activating Token Index: 584

Text #9

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0538. Min Act: -0.0002

Data Index: 1132732 (C4 (Web Text))

Max Activating Token Index: 73

Text #10

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0530. Min Act: -0.0002

Data Index: 532873 (C4 (Web Text))

Max Activating Token Index: 407

Text #11

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0439. Min Act: -0.0002

Data Index: 495071 (C4 (Web Text))

Max Activating Token Index: 663

Text #12

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0510. Min Act: -0.0002

Data Index: 1218451 (C4 (Web Text))

Max Activating Token Index: 513

Text #13

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0515. Min Act: -0.0002

Data Index: 590428 (C4 (Web Text))

Max Activating Token Index: 487

Text #14

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0500. Min Act: -0.0002

Data Index: 132452 (C4 (Web Text))

Max Activating Token Index: 468

Text #15

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0497. Min Act: -0.0002

Data Index: 1041373 (C4 (Web Text))

Max Activating Token Index: 1009

Text #16

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0475. Min Act: -0.0002

Data Index: 339277 (C4 (Web Text))

Max Activating Token Index: 654

Text #17

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0465. Min Act: -0.0002

Data Index: 1211797 (C4 (Web Text))

Max Activating Token Index: 52

Text #18

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0471. Min Act: -0.0002

Data Index: 553039 (C4 (Web Text))

Max Activating Token Index: 111

Text #19

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0473. Min Act: -0.0002

Data Index: 1062119 (C4 (Web Text))

Max Activating Token Index: 668