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

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

Neuron 817 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: 0.7927. Min Range: -0.7927

Max Act: 0.7927. Min Act: -0.0002

Data Index: 369437 (C4 (Web Text))

Max Activating Token Index: 608

Text #1

Max Range: 0.7927. Min Range: -0.7927

Max Act: 0.7675. Min Act: -0.0002

Data Index: 319096 (C4 (Web Text))

Max Activating Token Index: 210

Text #2

Max Range: 0.7927. Min Range: -0.7927

Max Act: 0.6359. Min Act: -0.0002

Data Index: 387907 (C4 (Web Text))

Max Activating Token Index: 146

Text #3

Max Range: 0.7927. Min Range: -0.7927

Max Act: 0.6351. Min Act: -0.0002

Data Index: 731656 (C4 (Web Text))

Max Activating Token Index: 660

Text #4

Max Range: 0.7927. Min Range: -0.7927

Max Act: 0.6482. Min Act: -0.0002

Data Index: 1435662 (Python Code)

Max Activating Token Index: 663

Text #5

Max Range: 0.7927. Min Range: -0.7927

Max Act: 0.6445. Min Act: -0.0002

Data Index: 1116736 (C4 (Web Text))

Max Activating Token Index: 382

Text #6

Max Range: 0.7927. Min Range: -0.7927

Max Act: 0.6376. Min Act: -0.0002

Data Index: 985342 (C4 (Web Text))

Max Activating Token Index: 98

Text #7

Max Range: 0.7927. Min Range: -0.7927

Max Act: 0.6017. Min Act: -0.0002

Data Index: 1378736 (Python Code)

Max Activating Token Index: 204

Text #8

Max Range: 0.7927. Min Range: -0.7927

Max Act: 0.5792. Min Act: -0.0002

Data Index: 1480267 (Python Code)

Max Activating Token Index: 435

Text #9

Max Range: 0.7927. Min Range: -0.7927

Max Act: 0.5743. Min Act: -0.0002

Data Index: 1233458 (C4 (Web Text))

Max Activating Token Index: 695

Text #10

Max Range: 0.7927. Min Range: -0.7927

Max Act: 0.5624. Min Act: -0.0002

Data Index: 1463018 (Python Code)

Max Activating Token Index: 63

Text #11

Max Range: 0.7927. Min Range: -0.7927

Max Act: 0.5607. Min Act: -0.0002

Data Index: 1165329 (C4 (Web Text))

Max Activating Token Index: 168

Text #12

Max Range: 0.7927. Min Range: -0.7927

Max Act: 0.5492. Min Act: -0.0002

Data Index: 679398 (C4 (Web Text))

Max Activating Token Index: 702

Text #13

Max Range: 0.7927. Min Range: -0.7927

Max Act: 0.5430. Min Act: -0.0002

Data Index: 732623 (C4 (Web Text))

Max Activating Token Index: 101

Text #14

Max Range: 0.7927. Min Range: -0.7927

Max Act: 0.5409. Min Act: -0.0002

Data Index: 1384110 (Python Code)

Max Activating Token Index: 545

Text #15

Max Range: 0.7927. Min Range: -0.7927

Max Act: 0.5327. Min Act: -0.0002

Data Index: 1395703 (Python Code)

Max Activating Token Index: 506

Text #16

Max Range: 0.7927. Min Range: -0.7927

Max Act: 0.5118. Min Act: -0.0002

Data Index: 206639 (C4 (Web Text))

Max Activating Token Index: 473

Text #17

Max Range: 0.7927. Min Range: -0.7927

Max Act: 0.5259. Min Act: -0.0002

Data Index: 1390587 (Python Code)

Max Activating Token Index: 66

Text #18

Max Range: 0.7927. Min Range: -0.7927

Max Act: 0.5436. Min Act: -0.0002

Data Index: 535933 (C4 (Web Text))

Max Activating Token Index: 820

Text #19

Max Range: 0.7927. Min Range: -0.7927

Max Act: 0.5094. Min Act: -0.0002

Data Index: 8191 (C4 (Web Text))

Max Activating Token Index: 292