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

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

Neuron 1513 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1787. Min Range: -2.1787

Max Act: 2.1787. Min Act: -0.0000

Data Index: 782370 (C4 (Web Text))

Max Activating Token Index: 188

Text #1

Max Range: 2.1787. Min Range: -2.1787

Max Act: 1.9539. Min Act: -0.0000

Data Index: 122578 (C4 (Web Text))

Max Activating Token Index: 104

Text #2

Max Range: 2.1787. Min Range: -2.1787

Max Act: 1.5913. Min Act: -0.0000

Data Index: 442955 (C4 (Web Text))

Max Activating Token Index: 259

Text #3

Max Range: 2.1787. Min Range: -2.1787

Max Act: 1.5271. Min Act: -0.0000

Data Index: 1152722 (C4 (Web Text))

Max Activating Token Index: 129

Text #4

Max Range: 2.1787. Min Range: -2.1787

Max Act: 1.6246. Min Act: -0.0000

Data Index: 779926 (C4 (Web Text))

Max Activating Token Index: 669

Text #5

Max Range: 2.1787. Min Range: -2.1787

Max Act: 1.5066. Min Act: -0.0000

Data Index: 687631 (C4 (Web Text))

Max Activating Token Index: 578

Text #6

Max Range: 2.1787. Min Range: -2.1787

Max Act: 1.6055. Min Act: -0.0000

Data Index: 662087 (C4 (Web Text))

Max Activating Token Index: 564

Text #7

Max Range: 2.1787. Min Range: -2.1787

Max Act: 1.4908. Min Act: -0.0000

Data Index: 573868 (C4 (Web Text))

Max Activating Token Index: 654

Text #8

Max Range: 2.1787. Min Range: -2.1787

Max Act: 1.4618. Min Act: -0.0000

Data Index: 432596 (C4 (Web Text))

Max Activating Token Index: 914

Text #9

Max Range: 2.1787. Min Range: -2.1787

Max Act: 1.4744. Min Act: -0.0000

Data Index: 829220 (C4 (Web Text))

Max Activating Token Index: 659

Text #10

Max Range: 2.1787. Min Range: -2.1787

Max Act: 1.4172. Min Act: -0.0000

Data Index: 938770 (C4 (Web Text))

Max Activating Token Index: 362

Text #11

Max Range: 2.1787. Min Range: -2.1787

Max Act: 1.3312. Min Act: -0.0000

Data Index: 1354814 (C4 (Web Text))

Max Activating Token Index: 466

Text #12

Max Range: 2.1787. Min Range: -2.1787

Max Act: 1.4329. Min Act: -0.0000

Data Index: 563320 (C4 (Web Text))

Max Activating Token Index: 955

Text #13

Max Range: 2.1787. Min Range: -2.1787

Max Act: 1.2624. Min Act: -0.0000

Data Index: 24206 (C4 (Web Text))

Max Activating Token Index: 635

Text #14

Max Range: 2.1787. Min Range: -2.1787

Max Act: 1.2997. Min Act: -0.0000

Data Index: 787575 (C4 (Web Text))

Max Activating Token Index: 217

Text #15

Max Range: 2.1787. Min Range: -2.1787

Max Act: 1.3244. Min Act: -0.0000

Data Index: 961969 (C4 (Web Text))

Max Activating Token Index: 310

Text #16

Max Range: 2.1787. Min Range: -2.1787

Max Act: 1.2864. Min Act: -0.0000

Data Index: 658060 (C4 (Web Text))

Max Activating Token Index: 208

Text #17

Max Range: 2.1787. Min Range: -2.1787

Max Act: 1.3498. Min Act: -0.0000

Data Index: 116735 (C4 (Web Text))

Max Activating Token Index: 772

Text #18

Max Range: 2.1787. Min Range: -2.1787

Max Act: 1.2833. Min Act: -0.0000

Data Index: 1310320 (C4 (Web Text))

Max Activating Token Index: 635

Text #19

Max Range: 2.1787. Min Range: -2.1787

Max Act: 1.2569. Min Act: -0.0000

Data Index: 1178670 (C4 (Web Text))

Max Activating Token Index: 655