Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 815 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0536. Min Act: -0.0002

Data Index: 797491 (C4 (Web Text))

Max Activating Token Index: 83

Text #1

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0492. Min Act: -0.0003

Data Index: 1336093 (C4 (Web Text))

Max Activating Token Index: 228

Text #2

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0487. Min Act: -0.0003

Data Index: 1167225 (C4 (Web Text))

Max Activating Token Index: 509

Text #3

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0476. Min Act: -0.0003

Data Index: 655602 (C4 (Web Text))

Max Activating Token Index: 972

Text #4

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0482. Min Act: -0.0003

Data Index: 625467 (C4 (Web Text))

Max Activating Token Index: 247

Text #5

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0493. Min Act: -0.0003

Data Index: 335223 (C4 (Web Text))

Max Activating Token Index: 80

Text #6

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0469. Min Act: -0.0003

Data Index: 1334252 (C4 (Web Text))

Max Activating Token Index: 871

Text #7

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0468. Min Act: -0.0002

Data Index: 883267 (C4 (Web Text))

Max Activating Token Index: 167

Text #8

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0456. Min Act: -0.0003

Data Index: 709945 (C4 (Web Text))

Max Activating Token Index: 431

Text #9

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0437. Min Act: -0.0002

Data Index: 908536 (C4 (Web Text))

Max Activating Token Index: 159

Text #10

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0465. Min Act: -0.0003

Data Index: 416006 (C4 (Web Text))

Max Activating Token Index: 879

Text #11

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0449. Min Act: -0.0003

Data Index: 1222234 (C4 (Web Text))

Max Activating Token Index: 189

Text #12

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0438. Min Act: -0.0003

Data Index: 985848 (C4 (Web Text))

Max Activating Token Index: 430

Text #13

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0437. Min Act: -0.0003

Data Index: 53993 (C4 (Web Text))

Max Activating Token Index: 268

Text #14

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0434. Min Act: -0.0002

Data Index: 507448 (C4 (Web Text))

Max Activating Token Index: 1000

Text #15

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0428. Min Act: -0.0003

Data Index: 376939 (C4 (Web Text))

Max Activating Token Index: 723

Text #16

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0436. Min Act: -0.0003

Data Index: 736743 (C4 (Web Text))

Max Activating Token Index: 544

Text #17

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0443. Min Act: -0.0003

Data Index: 778581 (C4 (Web Text))

Max Activating Token Index: 404

Text #18

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0427. Min Act: -0.0002

Data Index: 1083742 (C4 (Web Text))

Max Activating Token Index: 109

Text #19

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0442. Min Act: -0.0001

Data Index: 1291124 (C4 (Web Text))

Max Activating Token Index: 82