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

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

Neuron 566 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5432. Min Range: -1.5432

Max Act: 1.5432. Min Act: -0.0000

Data Index: 869131 (C4 (Web Text))

Max Activating Token Index: 340

Text #1

Max Range: 1.5432. Min Range: -1.5432

Max Act: 1.5373. Min Act: -0.0000

Data Index: 464852 (C4 (Web Text))

Max Activating Token Index: 656

Text #2

Max Range: 1.5432. Min Range: -1.5432

Max Act: 1.4935. Min Act: -0.0000

Data Index: 168926 (C4 (Web Text))

Max Activating Token Index: 625

Text #3

Max Range: 1.5432. Min Range: -1.5432

Max Act: 1.4230. Min Act: 0.0000

Data Index: 585819 (C4 (Web Text))

Max Activating Token Index: 130

Text #4

Max Range: 1.5432. Min Range: -1.5432

Max Act: 1.2840. Min Act: -0.0000

Data Index: 137600 (C4 (Web Text))

Max Activating Token Index: 69

Text #5

Max Range: 1.5432. Min Range: -1.5432

Max Act: 1.2108. Min Act: -0.0000

Data Index: 391120 (C4 (Web Text))

Max Activating Token Index: 681

Text #6

Max Range: 1.5432. Min Range: -1.5432

Max Act: 1.0998. Min Act: -0.0000

Data Index: 855659 (C4 (Web Text))

Max Activating Token Index: 978

Text #7

Max Range: 1.5432. Min Range: -1.5432

Max Act: 1.0548. Min Act: -0.0000

Data Index: 329025 (C4 (Web Text))

Max Activating Token Index: 858

Text #8

Max Range: 1.5432. Min Range: -1.5432

Max Act: 1.1162. Min Act: 0.0000

Data Index: 644361 (C4 (Web Text))

Max Activating Token Index: 383

Text #9

Max Range: 1.5432. Min Range: -1.5432

Max Act: 1.1229. Min Act: -0.0000

Data Index: 562902 (C4 (Web Text))

Max Activating Token Index: 114

Text #10

Max Range: 1.5432. Min Range: -1.5432

Max Act: 1.0733. Min Act: -0.0000

Data Index: 1134661 (C4 (Web Text))

Max Activating Token Index: 681

Text #11

Max Range: 1.5432. Min Range: -1.5432

Max Act: 1.0678. Min Act: -0.0000

Data Index: 368488 (C4 (Web Text))

Max Activating Token Index: 36

Text #12

Max Range: 1.5432. Min Range: -1.5432

Max Act: 0.9481. Min Act: -0.0000

Data Index: 510069 (C4 (Web Text))

Max Activating Token Index: 576

Text #13

Max Range: 1.5432. Min Range: -1.5432

Max Act: 0.9212. Min Act: -0.0000

Data Index: 1114943 (C4 (Web Text))

Max Activating Token Index: 898

Text #14

Max Range: 1.5432. Min Range: -1.5432

Max Act: 0.8801. Min Act: -0.0000

Data Index: 1049048 (C4 (Web Text))

Max Activating Token Index: 486

Text #15

Max Range: 1.5432. Min Range: -1.5432

Max Act: 0.8912. Min Act: -0.0000

Data Index: 526199 (C4 (Web Text))

Max Activating Token Index: 685

Text #16

Max Range: 1.5432. Min Range: -1.5432

Max Act: 0.8738. Min Act: -0.0000

Data Index: 372378 (C4 (Web Text))

Max Activating Token Index: 109

Text #17

Max Range: 1.5432. Min Range: -1.5432

Max Act: 0.9041. Min Act: -0.0000

Data Index: 897824 (C4 (Web Text))

Max Activating Token Index: 968

Text #18

Max Range: 1.5432. Min Range: -1.5432

Max Act: 0.8338. Min Act: 0.0000

Data Index: 47380 (C4 (Web Text))

Max Activating Token Index: 406

Text #19

Max Range: 1.5432. Min Range: -1.5432

Max Act: 0.9036. Min Act: 0.0000

Data Index: 583835 (C4 (Web Text))

Max Activating Token Index: 411