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

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

Neuron 5798 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0826. Min Range: -2.0826

Max Act: 2.0826. Min Act: -0.0000

Data Index: 878192 (C4 (Web Text))

Max Activating Token Index: 271

Text #1

Max Range: 2.0826. Min Range: -2.0826

Max Act: 1.9832. Min Act: -0.0000

Data Index: 1342573 (C4 (Web Text))

Max Activating Token Index: 564

Text #2

Max Range: 2.0826. Min Range: -2.0826

Max Act: 1.8561. Min Act: -0.0000

Data Index: 722073 (C4 (Web Text))

Max Activating Token Index: 281

Text #3

Max Range: 2.0826. Min Range: -2.0826

Max Act: 1.8237. Min Act: -0.0000

Data Index: 162332 (C4 (Web Text))

Max Activating Token Index: 54

Text #4

Max Range: 2.0826. Min Range: -2.0826

Max Act: 1.5823. Min Act: -0.0000

Data Index: 757601 (C4 (Web Text))

Max Activating Token Index: 111

Text #5

Max Range: 2.0826. Min Range: -2.0826

Max Act: 1.4537. Min Act: -0.0000

Data Index: 206095 (C4 (Web Text))

Max Activating Token Index: 88

Text #6

Max Range: 2.0826. Min Range: -2.0826

Max Act: 1.4413. Min Act: -0.0000

Data Index: 289494 (C4 (Web Text))

Max Activating Token Index: 441

Text #7

Max Range: 2.0826. Min Range: -2.0826

Max Act: 1.3571. Min Act: -0.0000

Data Index: 101008 (C4 (Web Text))

Max Activating Token Index: 750

Text #8

Max Range: 2.0826. Min Range: -2.0826

Max Act: 1.3448. Min Act: -0.0000

Data Index: 529637 (C4 (Web Text))

Max Activating Token Index: 106

Text #9

Max Range: 2.0826. Min Range: -2.0826

Max Act: 1.4054. Min Act: -0.0000

Data Index: 758410 (C4 (Web Text))

Max Activating Token Index: 846

Text #10

Max Range: 2.0826. Min Range: -2.0826

Max Act: 1.2377. Min Act: -0.0000

Data Index: 45674 (C4 (Web Text))

Max Activating Token Index: 580

Text #11

Max Range: 2.0826. Min Range: -2.0826

Max Act: 1.3078. Min Act: -0.0000

Data Index: 358424 (C4 (Web Text))

Max Activating Token Index: 638

Text #12

Max Range: 2.0826. Min Range: -2.0826

Max Act: 1.2246. Min Act: -0.0000

Data Index: 886351 (C4 (Web Text))

Max Activating Token Index: 225

Text #13

Max Range: 2.0826. Min Range: -2.0826

Max Act: 1.2290. Min Act: -0.0000

Data Index: 551609 (C4 (Web Text))

Max Activating Token Index: 976

Text #14

Max Range: 2.0826. Min Range: -2.0826

Max Act: 1.2914. Min Act: -0.0000

Data Index: 786728 (C4 (Web Text))

Max Activating Token Index: 49

Text #15

Max Range: 2.0826. Min Range: -2.0826

Max Act: 1.2203. Min Act: -0.0000

Data Index: 1114597 (C4 (Web Text))

Max Activating Token Index: 371

Text #16

Max Range: 2.0826. Min Range: -2.0826

Max Act: 1.1907. Min Act: -0.0000

Data Index: 602928 (C4 (Web Text))

Max Activating Token Index: 591

Text #17

Max Range: 2.0826. Min Range: -2.0826

Max Act: 0.9742. Min Act: -0.0000

Data Index: 216433 (C4 (Web Text))

Max Activating Token Index: 837

Text #18

Max Range: 2.0826. Min Range: -2.0826

Max Act: 1.1998. Min Act: -0.0000

Data Index: 923385 (C4 (Web Text))

Max Activating Token Index: 546

Text #19

Max Range: 2.0826. Min Range: -2.0826

Max Act: 1.1821. Min Act: -0.0000

Data Index: 364984 (C4 (Web Text))

Max Activating Token Index: 60