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

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

Neuron 4988 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5520. Min Range: -0.5520

Max Act: 0.5520. Min Act: -0.0002

Data Index: 84285 (C4 (Web Text))

Max Activating Token Index: 80

Text #1

Max Range: 0.5520. Min Range: -0.5520

Max Act: 0.5294. Min Act: -0.0002

Data Index: 287478 (C4 (Web Text))

Max Activating Token Index: 825

Text #2

Max Range: 0.5520. Min Range: -0.5520

Max Act: 0.5389. Min Act: -0.0002

Data Index: 1099843 (C4 (Web Text))

Max Activating Token Index: 601

Text #3

Max Range: 0.5520. Min Range: -0.5520

Max Act: 0.5105. Min Act: -0.0002

Data Index: 781115 (C4 (Web Text))

Max Activating Token Index: 672

Text #4

Max Range: 0.5520. Min Range: -0.5520

Max Act: 0.5282. Min Act: -0.0002

Data Index: 350700 (C4 (Web Text))

Max Activating Token Index: 452

Text #5

Max Range: 0.5520. Min Range: -0.5520

Max Act: 0.5211. Min Act: -0.0002

Data Index: 901391 (C4 (Web Text))

Max Activating Token Index: 410

Text #6

Max Range: 0.5520. Min Range: -0.5520

Max Act: 0.4844. Min Act: -0.0002

Data Index: 1135585 (C4 (Web Text))

Max Activating Token Index: 759

Text #7

Max Range: 0.5520. Min Range: -0.5520

Max Act: 0.5109. Min Act: -0.0002

Data Index: 829884 (C4 (Web Text))

Max Activating Token Index: 635

Text #8

Max Range: 0.5520. Min Range: -0.5520

Max Act: 0.4849. Min Act: -0.0002

Data Index: 1239922 (C4 (Web Text))

Max Activating Token Index: 643

Text #9

Max Range: 0.5520. Min Range: -0.5520

Max Act: 0.4610. Min Act: -0.0002

Data Index: 1244445 (C4 (Web Text))

Max Activating Token Index: 866

Text #10

Max Range: 0.5520. Min Range: -0.5520

Max Act: 0.4563. Min Act: -0.0002

Data Index: 104780 (C4 (Web Text))

Max Activating Token Index: 143

Text #11

Max Range: 0.5520. Min Range: -0.5520

Max Act: 0.4413. Min Act: -0.0002

Data Index: 368076 (C4 (Web Text))

Max Activating Token Index: 168

Text #12

Max Range: 0.5520. Min Range: -0.5520

Max Act: 0.4187. Min Act: -0.0002

Data Index: 878934 (C4 (Web Text))

Max Activating Token Index: 307

Text #13

Max Range: 0.5520. Min Range: -0.5520

Max Act: 0.4160. Min Act: -0.0002

Data Index: 747170 (C4 (Web Text))

Max Activating Token Index: 726

Text #14

Max Range: 0.5520. Min Range: -0.5520

Max Act: 0.4304. Min Act: -0.0002

Data Index: 192957 (C4 (Web Text))

Max Activating Token Index: 309

Text #15

Max Range: 0.5520. Min Range: -0.5520

Max Act: 0.4843. Min Act: -0.0002

Data Index: 1218838 (C4 (Web Text))

Max Activating Token Index: 515

Text #16

Max Range: 0.5520. Min Range: -0.5520

Max Act: 0.4388. Min Act: -0.0002

Data Index: 736536 (C4 (Web Text))

Max Activating Token Index: 69

Text #17

Max Range: 0.5520. Min Range: -0.5520

Max Act: 0.4107. Min Act: -0.0002

Data Index: 62229 (C4 (Web Text))

Max Activating Token Index: 275

Text #18

Max Range: 0.5520. Min Range: -0.5520

Max Act: 0.4351. Min Act: -0.0002

Data Index: 1156786 (C4 (Web Text))

Max Activating Token Index: 426

Text #19

Max Range: 0.5520. Min Range: -0.5520

Max Act: 0.4483. Min Act: -0.0002

Data Index: 535981 (C4 (Web Text))

Max Activating Token Index: 118