Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1947 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.9770. Min Range: -1.9770

Max Act: 1.9770. Min Act: -0.0000

Data Index: 95178 (C4 (Web Text))

Max Activating Token Index: 287

Text #1

Max Range: 1.9770. Min Range: -1.9770

Max Act: 1.9450. Min Act: -0.0000

Data Index: 1076516 (C4 (Web Text))

Max Activating Token Index: 670

Text #2

Max Range: 1.9770. Min Range: -1.9770

Max Act: 1.7929. Min Act: -0.0000

Data Index: 125336 (C4 (Web Text))

Max Activating Token Index: 386

Text #3

Max Range: 1.9770. Min Range: -1.9770

Max Act: 1.6150. Min Act: -0.0000

Data Index: 201208 (C4 (Web Text))

Max Activating Token Index: 96

Text #4

Max Range: 1.9770. Min Range: -1.9770

Max Act: 1.3903. Min Act: -0.0000

Data Index: 236242 (C4 (Web Text))

Max Activating Token Index: 184

Text #5

Max Range: 1.9770. Min Range: -1.9770

Max Act: 1.5440. Min Act: -0.0000

Data Index: 818300 (C4 (Web Text))

Max Activating Token Index: 943

Text #6

Max Range: 1.9770. Min Range: -1.9770

Max Act: 1.4896. Min Act: -0.0000

Data Index: 1187810 (C4 (Web Text))

Max Activating Token Index: 376

Text #7

Max Range: 1.9770. Min Range: -1.9770

Max Act: 1.4820. Min Act: -0.0000

Data Index: 98843 (C4 (Web Text))

Max Activating Token Index: 339

Text #8

Max Range: 1.9770. Min Range: -1.9770

Max Act: 1.4297. Min Act: -0.0000

Data Index: 575444 (C4 (Web Text))

Max Activating Token Index: 123

Text #9

Max Range: 1.9770. Min Range: -1.9770

Max Act: 1.1847. Min Act: -0.0000

Data Index: 18287 (C4 (Web Text))

Max Activating Token Index: 998

Text #10

Max Range: 1.9770. Min Range: -1.9770

Max Act: 1.3394. Min Act: -0.0000

Data Index: 1273640 (C4 (Web Text))

Max Activating Token Index: 976

Text #11

Max Range: 1.9770. Min Range: -1.9770

Max Act: 1.3130. Min Act: -0.0000

Data Index: 1235380 (C4 (Web Text))

Max Activating Token Index: 733

Text #12

Max Range: 1.9770. Min Range: -1.9770

Max Act: 1.3231. Min Act: -0.0000

Data Index: 600098 (C4 (Web Text))

Max Activating Token Index: 725

Text #13

Max Range: 1.9770. Min Range: -1.9770

Max Act: 1.2237. Min Act: -0.0000

Data Index: 1073468 (C4 (Web Text))

Max Activating Token Index: 162

Text #14

Max Range: 1.9770. Min Range: -1.9770

Max Act: 1.2411. Min Act: -0.0000

Data Index: 463897 (C4 (Web Text))

Max Activating Token Index: 716

Text #15

Max Range: 1.9770. Min Range: -1.9770

Max Act: 1.3644. Min Act: -0.0000

Data Index: 123962 (C4 (Web Text))

Max Activating Token Index: 286

Text #16

Max Range: 1.9770. Min Range: -1.9770

Max Act: 1.2967. Min Act: -0.0000

Data Index: 1268171 (C4 (Web Text))

Max Activating Token Index: 370

Text #17

Max Range: 1.9770. Min Range: -1.9770

Max Act: 1.1994. Min Act: -0.0000

Data Index: 961769 (C4 (Web Text))

Max Activating Token Index: 216

Text #18

Max Range: 1.9770. Min Range: -1.9770

Max Act: 1.2454. Min Act: -0.0000

Data Index: 946531 (C4 (Web Text))

Max Activating Token Index: 227

Text #19

Max Range: 1.9770. Min Range: -1.9770

Max Act: 1.1841. Min Act: -0.0000

Data Index: 1053109 (C4 (Web Text))

Max Activating Token Index: 685