Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3947 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7838. Min Range: -0.7838

Max Act: 0.7754. Min Act: -0.0001

Data Index: 457234 (C4 (Web Text))

Max Activating Token Index: 683

Text #1

Max Range: 0.7838. Min Range: -0.7838

Max Act: 0.7838. Min Act: -0.0000

Data Index: 866304 (C4 (Web Text))

Max Activating Token Index: 953

Text #2

Max Range: 0.7838. Min Range: -0.7838

Max Act: 0.7264. Min Act: -0.0000

Data Index: 1338835 (C4 (Web Text))

Max Activating Token Index: 657

Text #3

Max Range: 0.7838. Min Range: -0.7838

Max Act: 0.6566. Min Act: -0.0000

Data Index: 565146 (C4 (Web Text))

Max Activating Token Index: 516

Text #4

Max Range: 0.7838. Min Range: -0.7838

Max Act: 0.6552. Min Act: -0.0000

Data Index: 134509 (C4 (Web Text))

Max Activating Token Index: 745

Text #5

Max Range: 0.7838. Min Range: -0.7838

Max Act: 0.5733. Min Act: -0.0000

Data Index: 42394 (C4 (Web Text))

Max Activating Token Index: 266

Text #6

Max Range: 0.7838. Min Range: -0.7838

Max Act: 0.6111. Min Act: -0.0001

Data Index: 405617 (C4 (Web Text))

Max Activating Token Index: 60

Text #7

Max Range: 0.7838. Min Range: -0.7838

Max Act: 0.5804. Min Act: -0.0000

Data Index: 874888 (C4 (Web Text))

Max Activating Token Index: 570

Text #8

Max Range: 0.7838. Min Range: -0.7838

Max Act: 0.5757. Min Act: -0.0001

Data Index: 928434 (C4 (Web Text))

Max Activating Token Index: 769

Text #9

Max Range: 0.7838. Min Range: -0.7838

Max Act: 0.5413. Min Act: -0.0000

Data Index: 1252327 (C4 (Web Text))

Max Activating Token Index: 773

Text #10

Max Range: 0.7838. Min Range: -0.7838

Max Act: 0.5602. Min Act: -0.0000

Data Index: 391038 (C4 (Web Text))

Max Activating Token Index: 990

Text #11

Max Range: 0.7838. Min Range: -0.7838

Max Act: 0.5424. Min Act: -0.0000

Data Index: 234330 (C4 (Web Text))

Max Activating Token Index: 740

Text #12

Max Range: 0.7838. Min Range: -0.7838

Max Act: 0.5751. Min Act: -0.0001

Data Index: 402029 (C4 (Web Text))

Max Activating Token Index: 357

Text #13

Max Range: 0.7838. Min Range: -0.7838

Max Act: 0.5501. Min Act: -0.0000

Data Index: 40984 (C4 (Web Text))

Max Activating Token Index: 971

Text #14

Max Range: 0.7838. Min Range: -0.7838

Max Act: 0.5489. Min Act: -0.0000

Data Index: 840530 (C4 (Web Text))

Max Activating Token Index: 802

Text #15

Max Range: 0.7838. Min Range: -0.7838

Max Act: 0.5493. Min Act: -0.0001

Data Index: 1293394 (C4 (Web Text))

Max Activating Token Index: 504

Text #16

Max Range: 0.7838. Min Range: -0.7838

Max Act: 0.5238. Min Act: -0.0000

Data Index: 995376 (C4 (Web Text))

Max Activating Token Index: 1015

Text #17

Max Range: 0.7838. Min Range: -0.7838

Max Act: 0.5406. Min Act: -0.0001

Data Index: 437149 (C4 (Web Text))

Max Activating Token Index: 682

Text #18

Max Range: 0.7838. Min Range: -0.7838

Max Act: 0.5200. Min Act: -0.0001

Data Index: 744241 (C4 (Web Text))

Max Activating Token Index: 810

Text #19

Max Range: 0.7838. Min Range: -0.7838

Max Act: 0.5145. Min Act: -0.0001

Data Index: 1139261 (C4 (Web Text))

Max Activating Token Index: 226