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

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

Neuron 2189 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7454. Min Range: -0.7454

Max Act: 0.7454. Min Act: -0.0000

Data Index: 37199 (C4 (Web Text))

Max Activating Token Index: 629

Text #1

Max Range: 0.7454. Min Range: -0.7454

Max Act: 0.6878. Min Act: -0.0000

Data Index: 173504 (C4 (Web Text))

Max Activating Token Index: 103

Text #2

Max Range: 0.7454. Min Range: -0.7454

Max Act: 0.6324. Min Act: -0.0000

Data Index: 339544 (C4 (Web Text))

Max Activating Token Index: 726

Text #3

Max Range: 0.7454. Min Range: -0.7454

Max Act: 0.6152. Min Act: -0.0000

Data Index: 580986 (C4 (Web Text))

Max Activating Token Index: 546

Text #4

Max Range: 0.7454. Min Range: -0.7454

Max Act: 0.6131. Min Act: -0.0000

Data Index: 10291 (C4 (Web Text))

Max Activating Token Index: 63

Text #5

Max Range: 0.7454. Min Range: -0.7454

Max Act: 0.6209. Min Act: -0.0000

Data Index: 1056341 (C4 (Web Text))

Max Activating Token Index: 272

Text #6

Max Range: 0.7454. Min Range: -0.7454

Max Act: 0.6033. Min Act: -0.0000

Data Index: 970383 (C4 (Web Text))

Max Activating Token Index: 75

Text #7

Max Range: 0.7454. Min Range: -0.7454

Max Act: 0.6074. Min Act: -0.0000

Data Index: 1173623 (C4 (Web Text))

Max Activating Token Index: 844

Text #8

Max Range: 0.7454. Min Range: -0.7454

Max Act: 0.5554. Min Act: -0.0000

Data Index: 311330 (C4 (Web Text))

Max Activating Token Index: 921

Text #9

Max Range: 0.7454. Min Range: -0.7454

Max Act: 0.5689. Min Act: -0.0000

Data Index: 1313558 (C4 (Web Text))

Max Activating Token Index: 74

Text #10

Max Range: 0.7454. Min Range: -0.7454

Max Act: 0.5406. Min Act: -0.0000

Data Index: 961723 (C4 (Web Text))

Max Activating Token Index: 733

Text #11

Max Range: 0.7454. Min Range: -0.7454

Max Act: 0.5851. Min Act: -0.0000

Data Index: 802624 (C4 (Web Text))

Max Activating Token Index: 650

Text #12

Max Range: 0.7454. Min Range: -0.7454

Max Act: 0.5217. Min Act: -0.0000

Data Index: 1311689 (C4 (Web Text))

Max Activating Token Index: 822

Text #13

Max Range: 0.7454. Min Range: -0.7454

Max Act: 0.5195. Min Act: -0.0000

Data Index: 648085 (C4 (Web Text))

Max Activating Token Index: 406

Text #14

Max Range: 0.7454. Min Range: -0.7454

Max Act: 0.4831. Min Act: -0.0000

Data Index: 937961 (C4 (Web Text))

Max Activating Token Index: 386

Text #15

Max Range: 0.7454. Min Range: -0.7454

Max Act: 0.5493. Min Act: -0.0000

Data Index: 152434 (C4 (Web Text))

Max Activating Token Index: 320

Text #16

Max Range: 0.7454. Min Range: -0.7454

Max Act: 0.5444. Min Act: -0.0000

Data Index: 28878 (C4 (Web Text))

Max Activating Token Index: 236

Text #17

Max Range: 0.7454. Min Range: -0.7454

Max Act: 0.4968. Min Act: -0.0000

Data Index: 602631 (C4 (Web Text))

Max Activating Token Index: 348

Text #18

Max Range: 0.7454. Min Range: -0.7454

Max Act: 0.5236. Min Act: -0.0000

Data Index: 117685 (C4 (Web Text))

Max Activating Token Index: 414

Text #19

Max Range: 0.7454. Min Range: -0.7454

Max Act: 0.4940. Min Act: -0.0000

Data Index: 1353851 (C4 (Web Text))

Max Activating Token Index: 934