Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1546 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.7311. Min Range: -0.7311

Max Act: 0.7077. Min Act: -0.0004

Data Index: 925592 (C4 (Web Text))

Max Activating Token Index: 144

Text #1

Max Range: 0.7311. Min Range: -0.7311

Max Act: 0.6456. Min Act: -0.0004

Data Index: 31779 (C4 (Web Text))

Max Activating Token Index: 315

Text #2

Max Range: 0.7311. Min Range: -0.7311

Max Act: 0.7311. Min Act: -0.0004

Data Index: 908107 (C4 (Web Text))

Max Activating Token Index: 594

Text #3

Max Range: 0.7311. Min Range: -0.7311

Max Act: 0.6490. Min Act: -0.0004

Data Index: 606287 (C4 (Web Text))

Max Activating Token Index: 672

Text #4

Max Range: 0.7311. Min Range: -0.7311

Max Act: 0.5883. Min Act: -0.0004

Data Index: 667199 (C4 (Web Text))

Max Activating Token Index: 496

Text #5

Max Range: 0.7311. Min Range: -0.7311

Max Act: 0.5682. Min Act: -0.0004

Data Index: 1344631 (C4 (Web Text))

Max Activating Token Index: 443

Text #6

Max Range: 0.7311. Min Range: -0.7311

Max Act: 0.5584. Min Act: -0.0004

Data Index: 1113645 (C4 (Web Text))

Max Activating Token Index: 979

Text #7

Max Range: 0.7311. Min Range: -0.7311

Max Act: 0.6186. Min Act: -0.0004

Data Index: 433958 (C4 (Web Text))

Max Activating Token Index: 598

Text #8

Max Range: 0.7311. Min Range: -0.7311

Max Act: 0.5580. Min Act: -0.0004

Data Index: 858929 (C4 (Web Text))

Max Activating Token Index: 67

Text #9

Max Range: 0.7311. Min Range: -0.7311

Max Act: 0.4906. Min Act: -0.0004

Data Index: 815748 (C4 (Web Text))

Max Activating Token Index: 261

Text #10

Max Range: 0.7311. Min Range: -0.7311

Max Act: 0.5333. Min Act: -0.0004

Data Index: 1164318 (C4 (Web Text))

Max Activating Token Index: 456

Text #11

Max Range: 0.7311. Min Range: -0.7311

Max Act: 0.5263. Min Act: -0.0004

Data Index: 610734 (C4 (Web Text))

Max Activating Token Index: 776

Text #12

Max Range: 0.7311. Min Range: -0.7311

Max Act: 0.5417. Min Act: -0.0004

Data Index: 839400 (C4 (Web Text))

Max Activating Token Index: 265

Text #13

Max Range: 0.7311. Min Range: -0.7311

Max Act: 0.5253. Min Act: -0.0004

Data Index: 222759 (C4 (Web Text))

Max Activating Token Index: 89

Text #14

Max Range: 0.7311. Min Range: -0.7311

Max Act: 0.5597. Min Act: -0.0004

Data Index: 675055 (C4 (Web Text))

Max Activating Token Index: 607

Text #15

Max Range: 0.7311. Min Range: -0.7311

Max Act: 0.5455. Min Act: -0.0004

Data Index: 595814 (C4 (Web Text))

Max Activating Token Index: 679

Text #16

Max Range: 0.7311. Min Range: -0.7311

Max Act: 0.5243. Min Act: -0.0004

Data Index: 351882 (C4 (Web Text))

Max Activating Token Index: 121

Text #17

Max Range: 0.7311. Min Range: -0.7311

Max Act: 0.5190. Min Act: -0.0004

Data Index: 111277 (C4 (Web Text))

Max Activating Token Index: 140

Text #18

Max Range: 0.7311. Min Range: -0.7311

Max Act: 0.5054. Min Act: -0.0004

Data Index: 141542 (C4 (Web Text))

Max Activating Token Index: 383

Text #19

Max Range: 0.7311. Min Range: -0.7311

Max Act: 0.4866. Min Act: -0.0004

Data Index: 834264 (C4 (Web Text))

Max Activating Token Index: 529