Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2534 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3573. Min Range: -0.3573

Max Act: 0.3442. Min Act: -0.0001

Data Index: 463623 (C4 (Web Text))

Max Activating Token Index: 590

Text #1

Max Range: 0.3573. Min Range: -0.3573

Max Act: 0.3573. Min Act: -0.0001

Data Index: 1095692 (C4 (Web Text))

Max Activating Token Index: 251

Text #2

Max Range: 0.3573. Min Range: -0.3573

Max Act: 0.2959. Min Act: -0.0001

Data Index: 49122 (C4 (Web Text))

Max Activating Token Index: 857

Text #3

Max Range: 0.3573. Min Range: -0.3573

Max Act: 0.3532. Min Act: -0.0001

Data Index: 622553 (C4 (Web Text))

Max Activating Token Index: 780

Text #4

Max Range: 0.3573. Min Range: -0.3573

Max Act: 0.3285. Min Act: -0.0001

Data Index: 347022 (C4 (Web Text))

Max Activating Token Index: 1014

Text #5

Max Range: 0.3573. Min Range: -0.3573

Max Act: 0.3066. Min Act: -0.0001

Data Index: 932312 (C4 (Web Text))

Max Activating Token Index: 555

Text #6

Max Range: 0.3573. Min Range: -0.3573

Max Act: 0.3337. Min Act: -0.0001

Data Index: 526992 (C4 (Web Text))

Max Activating Token Index: 1012

Text #7

Max Range: 0.3573. Min Range: -0.3573

Max Act: 0.2999. Min Act: -0.0001

Data Index: 128763 (C4 (Web Text))

Max Activating Token Index: 59

Text #8

Max Range: 0.3573. Min Range: -0.3573

Max Act: 0.2753. Min Act: -0.0001

Data Index: 1349976 (C4 (Web Text))

Max Activating Token Index: 542

Text #9

Max Range: 0.3573. Min Range: -0.3573

Max Act: 0.2823. Min Act: -0.0001

Data Index: 141170 (C4 (Web Text))

Max Activating Token Index: 676

Text #10

Max Range: 0.3573. Min Range: -0.3573

Max Act: 0.2915. Min Act: -0.0001

Data Index: 651293 (C4 (Web Text))

Max Activating Token Index: 582

Text #11

Max Range: 0.3573. Min Range: -0.3573

Max Act: 0.2753. Min Act: -0.0001

Data Index: 91216 (C4 (Web Text))

Max Activating Token Index: 422

Text #12

Max Range: 0.3573. Min Range: -0.3573

Max Act: 0.2730. Min Act: -0.0001

Data Index: 351324 (C4 (Web Text))

Max Activating Token Index: 434

Text #13

Max Range: 0.3573. Min Range: -0.3573

Max Act: 0.2622. Min Act: -0.0001

Data Index: 607709 (C4 (Web Text))

Max Activating Token Index: 447

Text #14

Max Range: 0.3573. Min Range: -0.3573

Max Act: 0.2474. Min Act: -0.0001

Data Index: 170562 (C4 (Web Text))

Max Activating Token Index: 513

Text #15

Max Range: 0.3573. Min Range: -0.3573

Max Act: 0.3012. Min Act: -0.0001

Data Index: 443780 (C4 (Web Text))

Max Activating Token Index: 326

Text #16

Max Range: 0.3573. Min Range: -0.3573

Max Act: 0.1937. Min Act: -0.0001

Data Index: 243522 (C4 (Web Text))

Max Activating Token Index: 655

Text #17

Max Range: 0.3573. Min Range: -0.3573

Max Act: 0.2608. Min Act: -0.0001

Data Index: 1236090 (C4 (Web Text))

Max Activating Token Index: 89

Text #18

Max Range: 0.3573. Min Range: -0.3573

Max Act: 0.2512. Min Act: -0.0001

Data Index: 298711 (C4 (Web Text))

Max Activating Token Index: 204

Text #19

Max Range: 0.3573. Min Range: -0.3573

Max Act: 0.2687. Min Act: -0.0001

Data Index: 1165880 (C4 (Web Text))

Max Activating Token Index: 857