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

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

Neuron 3792 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7349. Min Range: -0.7349

Max Act: 0.7349. Min Act: -0.0000

Data Index: 614714 (C4 (Web Text))

Max Activating Token Index: 349

Text #1

Max Range: 0.7349. Min Range: -0.7349

Max Act: 0.6725. Min Act: -0.0000

Data Index: 256385 (C4 (Web Text))

Max Activating Token Index: 331

Text #2

Max Range: 0.7349. Min Range: -0.7349

Max Act: 0.6222. Min Act: -0.0000

Data Index: 464370 (C4 (Web Text))

Max Activating Token Index: 632

Text #3

Max Range: 0.7349. Min Range: -0.7349

Max Act: 0.5743. Min Act: -0.0000

Data Index: 383865 (C4 (Web Text))

Max Activating Token Index: 54

Text #4

Max Range: 0.7349. Min Range: -0.7349

Max Act: 0.5963. Min Act: -0.0000

Data Index: 1241423 (C4 (Web Text))

Max Activating Token Index: 276

Text #5

Max Range: 0.7349. Min Range: -0.7349

Max Act: 0.5897. Min Act: -0.0000

Data Index: 1358885 (C4 (Web Text))

Max Activating Token Index: 526

Text #6

Max Range: 0.7349. Min Range: -0.7349

Max Act: 0.5287. Min Act: -0.0000

Data Index: 1022981 (C4 (Web Text))

Max Activating Token Index: 712

Text #7

Max Range: 0.7349. Min Range: -0.7349

Max Act: 0.5351. Min Act: -0.0000

Data Index: 654555 (C4 (Web Text))

Max Activating Token Index: 170

Text #8

Max Range: 0.7349. Min Range: -0.7349

Max Act: 0.5485. Min Act: -0.0000

Data Index: 203141 (C4 (Web Text))

Max Activating Token Index: 672

Text #9

Max Range: 0.7349. Min Range: -0.7349

Max Act: 0.5004. Min Act: -0.0000

Data Index: 1183542 (C4 (Web Text))

Max Activating Token Index: 481

Text #10

Max Range: 0.7349. Min Range: -0.7349

Max Act: 0.4976. Min Act: -0.0000

Data Index: 1098352 (C4 (Web Text))

Max Activating Token Index: 783

Text #11

Max Range: 0.7349. Min Range: -0.7349

Max Act: 0.4643. Min Act: -0.0000

Data Index: 264610 (C4 (Web Text))

Max Activating Token Index: 337

Text #12

Max Range: 0.7349. Min Range: -0.7349

Max Act: 0.4471. Min Act: -0.0000

Data Index: 621166 (C4 (Web Text))

Max Activating Token Index: 715

Text #13

Max Range: 0.7349. Min Range: -0.7349

Max Act: 0.4523. Min Act: -0.0000

Data Index: 18060 (C4 (Web Text))

Max Activating Token Index: 767

Text #14

Max Range: 0.7349. Min Range: -0.7349

Max Act: 0.4669. Min Act: -0.0000

Data Index: 1279629 (C4 (Web Text))

Max Activating Token Index: 536

Text #15

Max Range: 0.7349. Min Range: -0.7349

Max Act: 0.4437. Min Act: -0.0000

Data Index: 411586 (C4 (Web Text))

Max Activating Token Index: 615

Text #16

Max Range: 0.7349. Min Range: -0.7349

Max Act: 0.4138. Min Act: -0.0000

Data Index: 759780 (C4 (Web Text))

Max Activating Token Index: 430

Text #17

Max Range: 0.7349. Min Range: -0.7349

Max Act: 0.4208. Min Act: -0.0000

Data Index: 1245135 (C4 (Web Text))

Max Activating Token Index: 884

Text #18

Max Range: 0.7349. Min Range: -0.7349

Max Act: 0.4677. Min Act: -0.0000

Data Index: 553855 (C4 (Web Text))

Max Activating Token Index: 147

Text #19

Max Range: 0.7349. Min Range: -0.7349

Max Act: 0.4361. Min Act: -0.0000

Data Index: 204242 (C4 (Web Text))

Max Activating Token Index: 151