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

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

Neuron 1559 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7076. Min Range: -0.7076

Max Act: 0.7076. Min Act: -0.0000

Data Index: 578900 (C4 (Web Text))

Max Activating Token Index: 927

Text #1

Max Range: 0.7076. Min Range: -0.7076

Max Act: 0.6531. Min Act: -0.0000

Data Index: 754168 (C4 (Web Text))

Max Activating Token Index: 978

Text #2

Max Range: 0.7076. Min Range: -0.7076

Max Act: 0.6158. Min Act: -0.0000

Data Index: 164653 (C4 (Web Text))

Max Activating Token Index: 824

Text #3

Max Range: 0.7076. Min Range: -0.7076

Max Act: 0.4705. Min Act: -0.0000

Data Index: 470010 (C4 (Web Text))

Max Activating Token Index: 922

Text #4

Max Range: 0.7076. Min Range: -0.7076

Max Act: 0.4524. Min Act: -0.0000

Data Index: 1191562 (C4 (Web Text))

Max Activating Token Index: 1018

Text #5

Max Range: 0.7076. Min Range: -0.7076

Max Act: 0.4517. Min Act: -0.0000

Data Index: 189290 (C4 (Web Text))

Max Activating Token Index: 37

Text #6

Max Range: 0.7076. Min Range: -0.7076

Max Act: 0.4440. Min Act: -0.0000

Data Index: 111416 (C4 (Web Text))

Max Activating Token Index: 857

Text #7

Max Range: 0.7076. Min Range: -0.7076

Max Act: 0.4457. Min Act: -0.0000

Data Index: 1087292 (C4 (Web Text))

Max Activating Token Index: 163

Text #8

Max Range: 0.7076. Min Range: -0.7076

Max Act: 0.4201. Min Act: -0.0000

Data Index: 1020216 (C4 (Web Text))

Max Activating Token Index: 926

Text #9

Max Range: 0.7076. Min Range: -0.7076

Max Act: 0.4407. Min Act: -0.0000

Data Index: 955608 (C4 (Web Text))

Max Activating Token Index: 488

Text #10

Max Range: 0.7076. Min Range: -0.7076

Max Act: 0.4110. Min Act: -0.0000

Data Index: 1227403 (C4 (Web Text))

Max Activating Token Index: 515

Text #11

Max Range: 0.7076. Min Range: -0.7076

Max Act: 0.4204. Min Act: -0.0000

Data Index: 387313 (C4 (Web Text))

Max Activating Token Index: 169

Text #12

Max Range: 0.7076. Min Range: -0.7076

Max Act: 0.4081. Min Act: -0.0000

Data Index: 84558 (C4 (Web Text))

Max Activating Token Index: 738

Text #13

Max Range: 0.7076. Min Range: -0.7076

Max Act: 0.3949. Min Act: -0.0000

Data Index: 738719 (C4 (Web Text))

Max Activating Token Index: 765

Text #14

Max Range: 0.7076. Min Range: -0.7076

Max Act: 0.3921. Min Act: -0.0000

Data Index: 299141 (C4 (Web Text))

Max Activating Token Index: 148

Text #15

Max Range: 0.7076. Min Range: -0.7076

Max Act: 0.3797. Min Act: -0.0000

Data Index: 882998 (C4 (Web Text))

Max Activating Token Index: 1002

Text #16

Max Range: 0.7076. Min Range: -0.7076

Max Act: 0.3988. Min Act: -0.0000

Data Index: 748088 (C4 (Web Text))

Max Activating Token Index: 737

Text #17

Max Range: 0.7076. Min Range: -0.7076

Max Act: 0.3655. Min Act: -0.0000

Data Index: 495770 (C4 (Web Text))

Max Activating Token Index: 808

Text #18

Max Range: 0.7076. Min Range: -0.7076

Max Act: 0.3724. Min Act: -0.0000

Data Index: 109882 (C4 (Web Text))

Max Activating Token Index: 212

Text #19

Max Range: 0.7076. Min Range: -0.7076

Max Act: 0.3750. Min Act: -0.0000

Data Index: 809923 (C4 (Web Text))

Max Activating Token Index: 964