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

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

Neuron 3475 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: 0.9894. Min Range: -0.9894

Max Act: 0.9894. Min Act: -0.0000

Data Index: 830361 (C4 (Web Text))

Max Activating Token Index: 657

Text #1

Max Range: 0.9894. Min Range: -0.9894

Max Act: 0.9798. Min Act: -0.0000

Data Index: 1106769 (C4 (Web Text))

Max Activating Token Index: 362

Text #2

Max Range: 0.9894. Min Range: -0.9894

Max Act: 0.9356. Min Act: -0.0000

Data Index: 1263649 (C4 (Web Text))

Max Activating Token Index: 989

Text #3

Max Range: 0.9894. Min Range: -0.9894

Max Act: 0.8923. Min Act: -0.0000

Data Index: 588097 (C4 (Web Text))

Max Activating Token Index: 809

Text #4

Max Range: 0.9894. Min Range: -0.9894

Max Act: 0.8804. Min Act: -0.0000

Data Index: 823266 (C4 (Web Text))

Max Activating Token Index: 105

Text #5

Max Range: 0.9894. Min Range: -0.9894

Max Act: 0.8179. Min Act: -0.0000

Data Index: 461953 (C4 (Web Text))

Max Activating Token Index: 326

Text #6

Max Range: 0.9894. Min Range: -0.9894

Max Act: 0.8712. Min Act: -0.0000

Data Index: 185651 (C4 (Web Text))

Max Activating Token Index: 809

Text #7

Max Range: 0.9894. Min Range: -0.9894

Max Act: 0.8423. Min Act: -0.0000

Data Index: 500690 (C4 (Web Text))

Max Activating Token Index: 935

Text #8

Max Range: 0.9894. Min Range: -0.9894

Max Act: 0.8841. Min Act: -0.0000

Data Index: 345500 (C4 (Web Text))

Max Activating Token Index: 925

Text #9

Max Range: 0.9894. Min Range: -0.9894

Max Act: 0.8187. Min Act: 0.0000

Data Index: 764198 (C4 (Web Text))

Max Activating Token Index: 25

Text #10

Max Range: 0.9894. Min Range: -0.9894

Max Act: 0.8362. Min Act: -0.0000

Data Index: 917185 (C4 (Web Text))

Max Activating Token Index: 394

Text #11

Max Range: 0.9894. Min Range: -0.9894

Max Act: 0.7717. Min Act: -0.0000

Data Index: 187826 (C4 (Web Text))

Max Activating Token Index: 1007

Text #12

Max Range: 0.9894. Min Range: -0.9894

Max Act: 0.7762. Min Act: -0.0000

Data Index: 689830 (C4 (Web Text))

Max Activating Token Index: 252

Text #13

Max Range: 0.9894. Min Range: -0.9894

Max Act: 0.7558. Min Act: 0.0000

Data Index: 1312129 (C4 (Web Text))

Max Activating Token Index: 40

Text #14

Max Range: 0.9894. Min Range: -0.9894

Max Act: 0.7502. Min Act: -0.0000

Data Index: 1012744 (C4 (Web Text))

Max Activating Token Index: 84

Text #15

Max Range: 0.9894. Min Range: -0.9894

Max Act: 0.7434. Min Act: -0.0000

Data Index: 1310300 (C4 (Web Text))

Max Activating Token Index: 160

Text #16

Max Range: 0.9894. Min Range: -0.9894

Max Act: 0.6883. Min Act: -0.0000

Data Index: 943386 (C4 (Web Text))

Max Activating Token Index: 411

Text #17

Max Range: 0.9894. Min Range: -0.9894

Max Act: 0.6886. Min Act: -0.0000

Data Index: 273500 (C4 (Web Text))

Max Activating Token Index: 767

Text #18

Max Range: 0.9894. Min Range: -0.9894

Max Act: 0.7289. Min Act: -0.0000

Data Index: 1006469 (C4 (Web Text))

Max Activating Token Index: 1012

Text #19

Max Range: 0.9894. Min Range: -0.9894

Max Act: 0.7063. Min Act: -0.0000

Data Index: 816879 (C4 (Web Text))

Max Activating Token Index: 591