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

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

Neuron 2489 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3533. Min Range: -0.3533

Max Act: 0.3266. Min Act: -0.0000

Data Index: 1268090 (C4 (Web Text))

Max Activating Token Index: 537

Text #1

Max Range: 0.3533. Min Range: -0.3533

Max Act: 0.3237. Min Act: -0.0001

Data Index: 1334409 (C4 (Web Text))

Max Activating Token Index: 17

Text #2

Max Range: 0.3533. Min Range: -0.3533

Max Act: 0.3533. Min Act: -0.0000

Data Index: 404265 (C4 (Web Text))

Max Activating Token Index: 633

Text #3

Max Range: 0.3533. Min Range: -0.3533

Max Act: 0.3286. Min Act: -0.0000

Data Index: 1185236 (C4 (Web Text))

Max Activating Token Index: 273

Text #4

Max Range: 0.3533. Min Range: -0.3533

Max Act: 0.2720. Min Act: -0.0000

Data Index: 200164 (C4 (Web Text))

Max Activating Token Index: 211

Text #5

Max Range: 0.3533. Min Range: -0.3533

Max Act: 0.3035. Min Act: -0.0000

Data Index: 797103 (C4 (Web Text))

Max Activating Token Index: 1004

Text #6

Max Range: 0.3533. Min Range: -0.3533

Max Act: 0.3053. Min Act: -0.0000

Data Index: 255492 (C4 (Web Text))

Max Activating Token Index: 414

Text #7

Max Range: 0.3533. Min Range: -0.3533

Max Act: 0.3139. Min Act: -0.0001

Data Index: 1022653 (C4 (Web Text))

Max Activating Token Index: 451

Text #8

Max Range: 0.3533. Min Range: -0.3533

Max Act: 0.2892. Min Act: -0.0000

Data Index: 454389 (C4 (Web Text))

Max Activating Token Index: 933

Text #9

Max Range: 0.3533. Min Range: -0.3533

Max Act: 0.2735. Min Act: -0.0000

Data Index: 682783 (C4 (Web Text))

Max Activating Token Index: 844

Text #10

Max Range: 0.3533. Min Range: -0.3533

Max Act: 0.2747. Min Act: -0.0000

Data Index: 761794 (C4 (Web Text))

Max Activating Token Index: 363

Text #11

Max Range: 0.3533. Min Range: -0.3533

Max Act: 0.2773. Min Act: -0.0000

Data Index: 210720 (C4 (Web Text))

Max Activating Token Index: 393

Text #12

Max Range: 0.3533. Min Range: -0.3533

Max Act: 0.2661. Min Act: -0.0000

Data Index: 1117680 (C4 (Web Text))

Max Activating Token Index: 692

Text #13

Max Range: 0.3533. Min Range: -0.3533

Max Act: 0.2689. Min Act: -0.0000

Data Index: 925673 (C4 (Web Text))

Max Activating Token Index: 454

Text #14

Max Range: 0.3533. Min Range: -0.3533

Max Act: 0.2726. Min Act: -0.0000

Data Index: 5844 (C4 (Web Text))

Max Activating Token Index: 890

Text #15

Max Range: 0.3533. Min Range: -0.3533

Max Act: 0.2742. Min Act: -0.0000

Data Index: 480995 (C4 (Web Text))

Max Activating Token Index: 395

Text #16

Max Range: 0.3533. Min Range: -0.3533

Max Act: 0.2818. Min Act: -0.0000

Data Index: 1227370 (C4 (Web Text))

Max Activating Token Index: 989

Text #17

Max Range: 0.3533. Min Range: -0.3533

Max Act: 0.2700. Min Act: -0.0000

Data Index: 606464 (C4 (Web Text))

Max Activating Token Index: 976

Text #18

Max Range: 0.3533. Min Range: -0.3533

Max Act: 0.2459. Min Act: -0.0000

Data Index: 96423 (C4 (Web Text))

Max Activating Token Index: 961

Text #19

Max Range: 0.3533. Min Range: -0.3533

Max Act: 0.2789. Min Act: -0.0000

Data Index: 801807 (C4 (Web Text))

Max Activating Token Index: 572