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

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

Neuron 3167 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.2504. Min Range: -0.2504

Max Act: 0.2504. Min Act: -0.0002

Data Index: 1412109 (Python Code)

Max Activating Token Index: 48

Text #1

Max Range: 0.2504. Min Range: -0.2504

Max Act: 0.2385. Min Act: -0.0002

Data Index: 1654303 (Python Code)

Max Activating Token Index: 122

Text #2

Max Range: 0.2504. Min Range: -0.2504

Max Act: 0.2257. Min Act: -0.0002

Data Index: 501252 (C4 (Web Text))

Max Activating Token Index: 792

Text #3

Max Range: 0.2504. Min Range: -0.2504

Max Act: 0.2148. Min Act: -0.0002

Data Index: 851861 (C4 (Web Text))

Max Activating Token Index: 853

Text #4

Max Range: 0.2504. Min Range: -0.2504

Max Act: 0.2123. Min Act: -0.0002

Data Index: 302156 (C4 (Web Text))

Max Activating Token Index: 935

Text #5

Max Range: 0.2504. Min Range: -0.2504

Max Act: 0.2112. Min Act: -0.0002

Data Index: 1229130 (C4 (Web Text))

Max Activating Token Index: 260

Text #6

Max Range: 0.2504. Min Range: -0.2504

Max Act: 0.2107. Min Act: -0.0002

Data Index: 422965 (C4 (Web Text))

Max Activating Token Index: 773

Text #7

Max Range: 0.2504. Min Range: -0.2504

Max Act: 0.2071. Min Act: -0.0002

Data Index: 1574751 (Python Code)

Max Activating Token Index: 248

Text #8

Max Range: 0.2504. Min Range: -0.2504

Max Act: 0.2082. Min Act: -0.0002

Data Index: 787709 (C4 (Web Text))

Max Activating Token Index: 474

Text #9

Max Range: 0.2504. Min Range: -0.2504

Max Act: 0.2047. Min Act: -0.0002

Data Index: 130035 (C4 (Web Text))

Max Activating Token Index: 551

Text #10

Max Range: 0.2504. Min Range: -0.2504

Max Act: 0.2077. Min Act: -0.0002

Data Index: 1436221 (Python Code)

Max Activating Token Index: 920

Text #11

Max Range: 0.2504. Min Range: -0.2504

Max Act: 0.2097. Min Act: -0.0002

Data Index: 512781 (C4 (Web Text))

Max Activating Token Index: 397

Text #12

Max Range: 0.2504. Min Range: -0.2504

Max Act: 0.2063. Min Act: -0.0002

Data Index: 985045 (C4 (Web Text))

Max Activating Token Index: 456

Text #13

Max Range: 0.2504. Min Range: -0.2504

Max Act: 0.2035. Min Act: -0.0002

Data Index: 315120 (C4 (Web Text))

Max Activating Token Index: 64

Text #14

Max Range: 0.2504. Min Range: -0.2504

Max Act: 0.2045. Min Act: -0.0002

Data Index: 432378 (C4 (Web Text))

Max Activating Token Index: 676

Text #15

Max Range: 0.2504. Min Range: -0.2504

Max Act: 0.2046. Min Act: -0.0002

Data Index: 1368427 (Python Code)

Max Activating Token Index: 500

Text #16

Max Range: 0.2504. Min Range: -0.2504

Max Act: 0.2058. Min Act: -0.0002

Data Index: 985905 (C4 (Web Text))

Max Activating Token Index: 169

Text #17

Max Range: 0.2504. Min Range: -0.2504

Max Act: 0.2025. Min Act: -0.0002

Data Index: 1371534 (Python Code)

Max Activating Token Index: 98

Text #18

Max Range: 0.2504. Min Range: -0.2504

Max Act: 0.2035. Min Act: -0.0002

Data Index: 857608 (C4 (Web Text))

Max Activating Token Index: 462

Text #19

Max Range: 0.2504. Min Range: -0.2504

Max Act: 0.2030. Min Act: -0.0002

Data Index: 721556 (C4 (Web Text))

Max Activating Token Index: 641