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

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

Neuron 5342 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1136. Min Range: -0.1136

Max Act: 0.1136. Min Act: -0.0000

Data Index: 1049233 (C4 (Web Text))

Max Activating Token Index: 220

Text #1

Max Range: 0.1136. Min Range: -0.1136

Max Act: 0.1083. Min Act: -0.0000

Data Index: 455432 (C4 (Web Text))

Max Activating Token Index: 515

Text #2

Max Range: 0.1136. Min Range: -0.1136

Max Act: 0.1049. Min Act: -0.0000

Data Index: 1098390 (C4 (Web Text))

Max Activating Token Index: 850

Text #3

Max Range: 0.1136. Min Range: -0.1136

Max Act: 0.1118. Min Act: -0.0000

Data Index: 297506 (C4 (Web Text))

Max Activating Token Index: 850

Text #4

Max Range: 0.1136. Min Range: -0.1136

Max Act: 0.0969. Min Act: -0.0000

Data Index: 666688 (C4 (Web Text))

Max Activating Token Index: 802

Text #5

Max Range: 0.1136. Min Range: -0.1136

Max Act: 0.0901. Min Act: -0.0000

Data Index: 1185717 (C4 (Web Text))

Max Activating Token Index: 668

Text #6

Max Range: 0.1136. Min Range: -0.1136

Max Act: 0.0914. Min Act: -0.0000

Data Index: 179240 (C4 (Web Text))

Max Activating Token Index: 114

Text #7

Max Range: 0.1136. Min Range: -0.1136

Max Act: 0.0911. Min Act: -0.0000

Data Index: 379972 (C4 (Web Text))

Max Activating Token Index: 697

Text #8

Max Range: 0.1136. Min Range: -0.1136

Max Act: 0.0907. Min Act: -0.0000

Data Index: 1134730 (C4 (Web Text))

Max Activating Token Index: 804

Text #9

Max Range: 0.1136. Min Range: -0.1136

Max Act: 0.0896. Min Act: -0.0000

Data Index: 1182206 (C4 (Web Text))

Max Activating Token Index: 750

Text #10

Max Range: 0.1136. Min Range: -0.1136

Max Act: 0.0851. Min Act: -0.0000

Data Index: 575134 (C4 (Web Text))

Max Activating Token Index: 500

Text #11

Max Range: 0.1136. Min Range: -0.1136

Max Act: 0.0824. Min Act: -0.0000

Data Index: 1040409 (C4 (Web Text))

Max Activating Token Index: 823

Text #12

Max Range: 0.1136. Min Range: -0.1136

Max Act: 0.0850. Min Act: -0.0000

Data Index: 472650 (C4 (Web Text))

Max Activating Token Index: 722

Text #13

Max Range: 0.1136. Min Range: -0.1136

Max Act: 0.0819. Min Act: -0.0000

Data Index: 222236 (C4 (Web Text))

Max Activating Token Index: 853

Text #14

Max Range: 0.1136. Min Range: -0.1136

Max Act: 0.0821. Min Act: -0.0000

Data Index: 646733 (C4 (Web Text))

Max Activating Token Index: 92

Text #15

Max Range: 0.1136. Min Range: -0.1136

Max Act: 0.0753. Min Act: -0.0000

Data Index: 1237954 (C4 (Web Text))

Max Activating Token Index: 665

Text #16

Max Range: 0.1136. Min Range: -0.1136

Max Act: 0.0783. Min Act: -0.0000

Data Index: 446618 (C4 (Web Text))

Max Activating Token Index: 556

Text #17

Max Range: 0.1136. Min Range: -0.1136

Max Act: 0.0810. Min Act: -0.0000

Data Index: 1253906 (C4 (Web Text))

Max Activating Token Index: 639

Text #18

Max Range: 0.1136. Min Range: -0.1136

Max Act: 0.0784. Min Act: -0.0000

Data Index: 40951 (C4 (Web Text))

Max Activating Token Index: 830

Text #19

Max Range: 0.1136. Min Range: -0.1136

Max Act: 0.0807. Min Act: -0.0000

Data Index: 829743 (C4 (Web Text))

Max Activating Token Index: 360