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

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

Neuron 1702 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5928. Min Range: -0.5928

Max Act: 0.5928. Min Act: -0.0002

Data Index: 633329 (C4 (Web Text))

Max Activating Token Index: 467

Text #1

Max Range: 0.5928. Min Range: -0.5928

Max Act: 0.4807. Min Act: -0.0002

Data Index: 1270479 (C4 (Web Text))

Max Activating Token Index: 978

Text #2

Max Range: 0.5928. Min Range: -0.5928

Max Act: 0.5026. Min Act: -0.0002

Data Index: 192896 (C4 (Web Text))

Max Activating Token Index: 976

Text #3

Max Range: 0.5928. Min Range: -0.5928

Max Act: 0.5194. Min Act: -0.0001

Data Index: 1328378 (C4 (Web Text))

Max Activating Token Index: 860

Text #4

Max Range: 0.5928. Min Range: -0.5928

Max Act: 0.4521. Min Act: -0.0002

Data Index: 1133827 (C4 (Web Text))

Max Activating Token Index: 806

Text #5

Max Range: 0.5928. Min Range: -0.5928

Max Act: 0.4812. Min Act: -0.0001

Data Index: 1219001 (C4 (Web Text))

Max Activating Token Index: 37

Text #6

Max Range: 0.5928. Min Range: -0.5928

Max Act: 0.4642. Min Act: -0.0001

Data Index: 1031639 (C4 (Web Text))

Max Activating Token Index: 598

Text #7

Max Range: 0.5928. Min Range: -0.5928

Max Act: 0.4791. Min Act: -0.0002

Data Index: 845415 (C4 (Web Text))

Max Activating Token Index: 680

Text #8

Max Range: 0.5928. Min Range: -0.5928

Max Act: 0.4428. Min Act: -0.0002

Data Index: 566363 (C4 (Web Text))

Max Activating Token Index: 712

Text #9

Max Range: 0.5928. Min Range: -0.5928

Max Act: 0.5040. Min Act: -0.0002

Data Index: 120953 (C4 (Web Text))

Max Activating Token Index: 847

Text #10

Max Range: 0.5928. Min Range: -0.5928

Max Act: 0.4585. Min Act: -0.0002

Data Index: 826654 (C4 (Web Text))

Max Activating Token Index: 370

Text #11

Max Range: 0.5928. Min Range: -0.5928

Max Act: 0.4170. Min Act: -0.0002

Data Index: 948209 (C4 (Web Text))

Max Activating Token Index: 391

Text #12

Max Range: 0.5928. Min Range: -0.5928

Max Act: 0.4896. Min Act: -0.0002

Data Index: 919379 (C4 (Web Text))

Max Activating Token Index: 517

Text #13

Max Range: 0.5928. Min Range: -0.5928

Max Act: 0.4418. Min Act: -0.0002

Data Index: 405198 (C4 (Web Text))

Max Activating Token Index: 753

Text #14

Max Range: 0.5928. Min Range: -0.5928

Max Act: 0.4528. Min Act: -0.0002

Data Index: 185780 (C4 (Web Text))

Max Activating Token Index: 853

Text #15

Max Range: 0.5928. Min Range: -0.5928

Max Act: 0.4542. Min Act: -0.0001

Data Index: 1069075 (C4 (Web Text))

Max Activating Token Index: 642

Text #16

Max Range: 0.5928. Min Range: -0.5928

Max Act: 0.4349. Min Act: -0.0002

Data Index: 671159 (C4 (Web Text))

Max Activating Token Index: 763

Text #17

Max Range: 0.5928. Min Range: -0.5928

Max Act: 0.4210. Min Act: -0.0002

Data Index: 1149220 (C4 (Web Text))

Max Activating Token Index: 492

Text #18

Max Range: 0.5928. Min Range: -0.5928

Max Act: 0.4187. Min Act: -0.0002

Data Index: 83474 (C4 (Web Text))

Max Activating Token Index: 563

Text #19

Max Range: 0.5928. Min Range: -0.5928

Max Act: 0.4307. Min Act: -0.0002

Data Index: 190512 (C4 (Web Text))

Max Activating Token Index: 851