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

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

Neuron 1500 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4211. Min Range: -1.4211

Max Act: 1.4211. Min Act: -0.0000

Data Index: 676067 (C4 (Web Text))

Max Activating Token Index: 613

Text #1

Max Range: 1.4211. Min Range: -1.4211

Max Act: 1.1251. Min Act: -0.0000

Data Index: 310690 (C4 (Web Text))

Max Activating Token Index: 571

Text #2

Max Range: 1.4211. Min Range: -1.4211

Max Act: 1.1126. Min Act: -0.0000

Data Index: 322443 (C4 (Web Text))

Max Activating Token Index: 584

Text #3

Max Range: 1.4211. Min Range: -1.4211

Max Act: 1.0920. Min Act: -0.0000

Data Index: 1187025 (C4 (Web Text))

Max Activating Token Index: 786

Text #4

Max Range: 1.4211. Min Range: -1.4211

Max Act: 0.9539. Min Act: -0.0000

Data Index: 1007373 (C4 (Web Text))

Max Activating Token Index: 888

Text #5

Max Range: 1.4211. Min Range: -1.4211

Max Act: 1.0687. Min Act: -0.0000

Data Index: 34260 (C4 (Web Text))

Max Activating Token Index: 321

Text #6

Max Range: 1.4211. Min Range: -1.4211

Max Act: 0.9296. Min Act: -0.0000

Data Index: 999626 (C4 (Web Text))

Max Activating Token Index: 67

Text #7

Max Range: 1.4211. Min Range: -1.4211

Max Act: 0.9899. Min Act: -0.0000

Data Index: 342566 (C4 (Web Text))

Max Activating Token Index: 101

Text #8

Max Range: 1.4211. Min Range: -1.4211

Max Act: 0.9748. Min Act: -0.0000

Data Index: 799724 (C4 (Web Text))

Max Activating Token Index: 137

Text #9

Max Range: 1.4211. Min Range: -1.4211

Max Act: 0.9668. Min Act: -0.0000

Data Index: 363004 (C4 (Web Text))

Max Activating Token Index: 643

Text #10

Max Range: 1.4211. Min Range: -1.4211

Max Act: 0.9680. Min Act: -0.0000

Data Index: 301023 (C4 (Web Text))

Max Activating Token Index: 270

Text #11

Max Range: 1.4211. Min Range: -1.4211

Max Act: 1.0737. Min Act: 0.0000

Data Index: 1107684 (C4 (Web Text))

Max Activating Token Index: 266

Text #12

Max Range: 1.4211. Min Range: -1.4211

Max Act: 0.9157. Min Act: -0.0000

Data Index: 167665 (C4 (Web Text))

Max Activating Token Index: 183

Text #13

Max Range: 1.4211. Min Range: -1.4211

Max Act: 0.9111. Min Act: -0.0000

Data Index: 379751 (C4 (Web Text))

Max Activating Token Index: 840

Text #14

Max Range: 1.4211. Min Range: -1.4211

Max Act: 0.8631. Min Act: -0.0000

Data Index: 265686 (C4 (Web Text))

Max Activating Token Index: 389

Text #15

Max Range: 1.4211. Min Range: -1.4211

Max Act: 0.9086. Min Act: -0.0000

Data Index: 1057954 (C4 (Web Text))

Max Activating Token Index: 499

Text #16

Max Range: 1.4211. Min Range: -1.4211

Max Act: 0.9633. Min Act: -0.0000

Data Index: 1024691 (C4 (Web Text))

Max Activating Token Index: 513

Text #17

Max Range: 1.4211. Min Range: -1.4211

Max Act: 0.9024. Min Act: -0.0000

Data Index: 1096555 (C4 (Web Text))

Max Activating Token Index: 138

Text #18

Max Range: 1.4211. Min Range: -1.4211

Max Act: 0.8926. Min Act: -0.0000

Data Index: 28148 (C4 (Web Text))

Max Activating Token Index: 288

Text #19

Max Range: 1.4211. Min Range: -1.4211

Max Act: 0.8835. Min Act: -0.0000

Data Index: 342445 (C4 (Web Text))

Max Activating Token Index: 79