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

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

Neuron 4482 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.4502. Min Range: -3.4502

Max Act: 3.4502. Min Act: -0.0000

Data Index: 131741 (C4 (Web Text))

Max Activating Token Index: 649

Text #1

Max Range: 3.4502. Min Range: -3.4502

Max Act: 2.6890. Min Act: -0.0000

Data Index: 926711 (C4 (Web Text))

Max Activating Token Index: 894

Text #2

Max Range: 3.4502. Min Range: -3.4502

Max Act: 2.4352. Min Act: -0.0000

Data Index: 1180676 (C4 (Web Text))

Max Activating Token Index: 23

Text #3

Max Range: 3.4502. Min Range: -3.4502

Max Act: 2.2273. Min Act: -0.0000

Data Index: 121349 (C4 (Web Text))

Max Activating Token Index: 876

Text #4

Max Range: 3.4502. Min Range: -3.4502

Max Act: 2.0105. Min Act: -0.0000

Data Index: 1044538 (C4 (Web Text))

Max Activating Token Index: 886

Text #5

Max Range: 3.4502. Min Range: -3.4502

Max Act: 1.7391. Min Act: -0.0000

Data Index: 514606 (C4 (Web Text))

Max Activating Token Index: 773

Text #6

Max Range: 3.4502. Min Range: -3.4502

Max Act: 1.8759. Min Act: -0.0000

Data Index: 1315610 (C4 (Web Text))

Max Activating Token Index: 527

Text #7

Max Range: 3.4502. Min Range: -3.4502

Max Act: 1.9191. Min Act: -0.0000

Data Index: 79730 (C4 (Web Text))

Max Activating Token Index: 962

Text #8

Max Range: 3.4502. Min Range: -3.4502

Max Act: 1.7524. Min Act: -0.0000

Data Index: 1216142 (C4 (Web Text))

Max Activating Token Index: 982

Text #9

Max Range: 3.4502. Min Range: -3.4502

Max Act: 1.6574. Min Act: -0.0000

Data Index: 25277 (C4 (Web Text))

Max Activating Token Index: 16

Text #10

Max Range: 3.4502. Min Range: -3.4502

Max Act: 1.5997. Min Act: -0.0000

Data Index: 903592 (C4 (Web Text))

Max Activating Token Index: 356

Text #11

Max Range: 3.4502. Min Range: -3.4502

Max Act: 1.4757. Min Act: -0.0000

Data Index: 1238922 (C4 (Web Text))

Max Activating Token Index: 689

Text #12

Max Range: 3.4502. Min Range: -3.4502

Max Act: 1.4738. Min Act: -0.0000

Data Index: 5540 (C4 (Web Text))

Max Activating Token Index: 915

Text #13

Max Range: 3.4502. Min Range: -3.4502

Max Act: 1.4455. Min Act: -0.0000

Data Index: 1136457 (C4 (Web Text))

Max Activating Token Index: 931

Text #14

Max Range: 3.4502. Min Range: -3.4502

Max Act: 1.5243. Min Act: -0.0000

Data Index: 757611 (C4 (Web Text))

Max Activating Token Index: 290

Text #15

Max Range: 3.4502. Min Range: -3.4502

Max Act: 1.2675. Min Act: -0.0000

Data Index: 489683 (C4 (Web Text))

Max Activating Token Index: 334

Text #16

Max Range: 3.4502. Min Range: -3.4502

Max Act: 1.5065. Min Act: -0.0000

Data Index: 978663 (C4 (Web Text))

Max Activating Token Index: 170

Text #17

Max Range: 3.4502. Min Range: -3.4502

Max Act: 1.6633. Min Act: -0.0000

Data Index: 428321 (C4 (Web Text))

Max Activating Token Index: 299

Text #18

Max Range: 3.4502. Min Range: -3.4502

Max Act: 1.5494. Min Act: -0.0000

Data Index: 1153346 (C4 (Web Text))

Max Activating Token Index: 603

Text #19

Max Range: 3.4502. Min Range: -3.4502

Max Act: 1.3544. Min Act: -0.0000

Data Index: 907196 (C4 (Web Text))

Max Activating Token Index: 991