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

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

Neuron 2035 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1733. Min Range: -5.1733

Max Act: 5.1584. Min Act: -0.0000

Data Index: 329231 (C4 (Web Text))

Max Activating Token Index: 46

Text #1

Max Range: 5.1733. Min Range: -5.1733

Max Act: 5.1640. Min Act: -0.0000

Data Index: 872841 (C4 (Web Text))

Max Activating Token Index: 32

Text #2

Max Range: 5.1733. Min Range: -5.1733

Max Act: 5.1167. Min Act: -0.0000

Data Index: 804972 (C4 (Web Text))

Max Activating Token Index: 369

Text #3

Max Range: 5.1733. Min Range: -5.1733

Max Act: 5.1733. Min Act: -0.0000

Data Index: 160536 (C4 (Web Text))

Max Activating Token Index: 428

Text #4

Max Range: 5.1733. Min Range: -5.1733

Max Act: 4.9913. Min Act: -0.0000

Data Index: 517523 (C4 (Web Text))

Max Activating Token Index: 53

Text #5

Max Range: 5.1733. Min Range: -5.1733

Max Act: 4.9865. Min Act: -0.0000

Data Index: 1336620 (C4 (Web Text))

Max Activating Token Index: 35

Text #6

Max Range: 5.1733. Min Range: -5.1733

Max Act: 4.1291. Min Act: -0.0000

Data Index: 1167040 (C4 (Web Text))

Max Activating Token Index: 743

Text #7

Max Range: 5.1733. Min Range: -5.1733

Max Act: 4.8108. Min Act: -0.0000

Data Index: 778886 (C4 (Web Text))

Max Activating Token Index: 162

Text #8

Max Range: 5.1733. Min Range: -5.1733

Max Act: 4.5656. Min Act: -0.0000

Data Index: 1344330 (C4 (Web Text))

Max Activating Token Index: 201

Text #9

Max Range: 5.1733. Min Range: -5.1733

Max Act: 4.3707. Min Act: -0.0000

Data Index: 640919 (C4 (Web Text))

Max Activating Token Index: 206

Text #10

Max Range: 5.1733. Min Range: -5.1733

Max Act: 4.3474. Min Act: -0.0000

Data Index: 754196 (C4 (Web Text))

Max Activating Token Index: 29

Text #11

Max Range: 5.1733. Min Range: -5.1733

Max Act: 5.0601. Min Act: -0.0000

Data Index: 486719 (C4 (Web Text))

Max Activating Token Index: 277

Text #12

Max Range: 5.1733. Min Range: -5.1733

Max Act: 4.3525. Min Act: -0.0000

Data Index: 634954 (C4 (Web Text))

Max Activating Token Index: 200

Text #13

Max Range: 5.1733. Min Range: -5.1733

Max Act: 4.6785. Min Act: -0.0000

Data Index: 1049305 (C4 (Web Text))

Max Activating Token Index: 40

Text #14

Max Range: 5.1733. Min Range: -5.1733

Max Act: 5.0703. Min Act: -0.0000

Data Index: 1227691 (C4 (Web Text))

Max Activating Token Index: 104

Text #15

Max Range: 5.1733. Min Range: -5.1733

Max Act: 4.3286. Min Act: -0.0000

Data Index: 608165 (C4 (Web Text))

Max Activating Token Index: 169

Text #16

Max Range: 5.1733. Min Range: -5.1733

Max Act: 4.4919. Min Act: -0.0000

Data Index: 692976 (C4 (Web Text))

Max Activating Token Index: 138

Text #17

Max Range: 5.1733. Min Range: -5.1733

Max Act: 4.3089. Min Act: -0.0000

Data Index: 842293 (C4 (Web Text))

Max Activating Token Index: 187

Text #18

Max Range: 5.1733. Min Range: -5.1733

Max Act: 4.3072. Min Act: -0.0000

Data Index: 623107 (C4 (Web Text))

Max Activating Token Index: 181

Text #19

Max Range: 5.1733. Min Range: -5.1733

Max Act: 4.6536. Min Act: -0.0000

Data Index: 1175537 (C4 (Web Text))

Max Activating Token Index: 226