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

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

Neuron 4894 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8922. Min Range: -2.8922

Max Act: 2.7964. Min Act: -0.0000

Data Index: 115716 (C4 (Web Text))

Max Activating Token Index: 409

Text #1

Max Range: 2.8922. Min Range: -2.8922

Max Act: 2.8922. Min Act: -0.0000

Data Index: 773074 (C4 (Web Text))

Max Activating Token Index: 33

Text #2

Max Range: 2.8922. Min Range: -2.8922

Max Act: 2.6018. Min Act: -0.0000

Data Index: 18852 (C4 (Web Text))

Max Activating Token Index: 39

Text #3

Max Range: 2.8922. Min Range: -2.8922

Max Act: 2.2151. Min Act: -0.0000

Data Index: 1217162 (C4 (Web Text))

Max Activating Token Index: 903

Text #4

Max Range: 2.8922. Min Range: -2.8922

Max Act: 2.4452. Min Act: -0.0000

Data Index: 221562 (C4 (Web Text))

Max Activating Token Index: 513

Text #5

Max Range: 2.8922. Min Range: -2.8922

Max Act: 2.4033. Min Act: -0.0000

Data Index: 1337600 (C4 (Web Text))

Max Activating Token Index: 260

Text #6

Max Range: 2.8922. Min Range: -2.8922

Max Act: 2.1046. Min Act: -0.0000

Data Index: 585644 (C4 (Web Text))

Max Activating Token Index: 269

Text #7

Max Range: 2.8922. Min Range: -2.8922

Max Act: 2.2715. Min Act: -0.0000

Data Index: 175982 (C4 (Web Text))

Max Activating Token Index: 386

Text #8

Max Range: 2.8922. Min Range: -2.8922

Max Act: 2.0185. Min Act: -0.0000

Data Index: 476411 (C4 (Web Text))

Max Activating Token Index: 271

Text #9

Max Range: 2.8922. Min Range: -2.8922

Max Act: 2.1094. Min Act: -0.0000

Data Index: 226430 (C4 (Web Text))

Max Activating Token Index: 12

Text #10

Max Range: 2.8922. Min Range: -2.8922

Max Act: 2.1141. Min Act: -0.0000

Data Index: 262554 (C4 (Web Text))

Max Activating Token Index: 534

Text #11

Max Range: 2.8922. Min Range: -2.8922

Max Act: 2.0376. Min Act: -0.0000

Data Index: 1174891 (C4 (Web Text))

Max Activating Token Index: 830

Text #12

Max Range: 2.8922. Min Range: -2.8922

Max Act: 2.0540. Min Act: -0.0000

Data Index: 82881 (C4 (Web Text))

Max Activating Token Index: 359

Text #13

Max Range: 2.8922. Min Range: -2.8922

Max Act: 2.1837. Min Act: -0.0000

Data Index: 1135446 (C4 (Web Text))

Max Activating Token Index: 302

Text #14

Max Range: 2.8922. Min Range: -2.8922

Max Act: 2.0137. Min Act: -0.0000

Data Index: 342118 (C4 (Web Text))

Max Activating Token Index: 35

Text #15

Max Range: 2.8922. Min Range: -2.8922

Max Act: 1.9764. Min Act: -0.0000

Data Index: 95904 (C4 (Web Text))

Max Activating Token Index: 1017

Text #16

Max Range: 2.8922. Min Range: -2.8922

Max Act: 2.0580. Min Act: -0.0000

Data Index: 1136647 (C4 (Web Text))

Max Activating Token Index: 740

Text #17

Max Range: 2.8922. Min Range: -2.8922

Max Act: 1.8326. Min Act: -0.0000

Data Index: 946961 (C4 (Web Text))

Max Activating Token Index: 278

Text #18

Max Range: 2.8922. Min Range: -2.8922

Max Act: 1.9192. Min Act: -0.0000

Data Index: 1110347 (C4 (Web Text))

Max Activating Token Index: 723

Text #19

Max Range: 2.8922. Min Range: -2.8922

Max Act: 1.9141. Min Act: -0.0000

Data Index: 888815 (C4 (Web Text))

Max Activating Token Index: 52