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

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

Neuron 146 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5152. Min Range: -2.5152

Max Act: 2.5152. Min Act: -0.0000

Data Index: 892880 (C4 (Web Text))

Max Activating Token Index: 702

Text #1

Max Range: 2.5152. Min Range: -2.5152

Max Act: 1.9859. Min Act: -0.0000

Data Index: 1012093 (C4 (Web Text))

Max Activating Token Index: 844

Text #2

Max Range: 2.5152. Min Range: -2.5152

Max Act: 2.3173. Min Act: -0.0000

Data Index: 1260644 (C4 (Web Text))

Max Activating Token Index: 36

Text #3

Max Range: 2.5152. Min Range: -2.5152

Max Act: 2.0966. Min Act: -0.0000

Data Index: 582684 (C4 (Web Text))

Max Activating Token Index: 67

Text #4

Max Range: 2.5152. Min Range: -2.5152

Max Act: 2.2292. Min Act: -0.0000

Data Index: 533963 (C4 (Web Text))

Max Activating Token Index: 603

Text #5

Max Range: 2.5152. Min Range: -2.5152

Max Act: 2.0689. Min Act: -0.0000

Data Index: 351245 (C4 (Web Text))

Max Activating Token Index: 260

Text #6

Max Range: 2.5152. Min Range: -2.5152

Max Act: 2.0960. Min Act: -0.0000

Data Index: 63092 (C4 (Web Text))

Max Activating Token Index: 871

Text #7

Max Range: 2.5152. Min Range: -2.5152

Max Act: 2.0765. Min Act: -0.0000

Data Index: 897904 (C4 (Web Text))

Max Activating Token Index: 587

Text #8

Max Range: 2.5152. Min Range: -2.5152

Max Act: 1.9426. Min Act: -0.0000

Data Index: 679872 (C4 (Web Text))

Max Activating Token Index: 747

Text #9

Max Range: 2.5152. Min Range: -2.5152

Max Act: 1.8508. Min Act: -0.0000

Data Index: 984193 (C4 (Web Text))

Max Activating Token Index: 666

Text #10

Max Range: 2.5152. Min Range: -2.5152

Max Act: 1.8346. Min Act: -0.0000

Data Index: 748802 (C4 (Web Text))

Max Activating Token Index: 163

Text #11

Max Range: 2.5152. Min Range: -2.5152

Max Act: 1.7386. Min Act: -0.0000

Data Index: 197088 (C4 (Web Text))

Max Activating Token Index: 100

Text #12

Max Range: 2.5152. Min Range: -2.5152

Max Act: 1.7795. Min Act: -0.0000

Data Index: 803460 (C4 (Web Text))

Max Activating Token Index: 920

Text #13

Max Range: 2.5152. Min Range: -2.5152

Max Act: 1.6781. Min Act: -0.0000

Data Index: 825577 (C4 (Web Text))

Max Activating Token Index: 148

Text #14

Max Range: 2.5152. Min Range: -2.5152

Max Act: 1.6904. Min Act: -0.0000

Data Index: 1144142 (C4 (Web Text))

Max Activating Token Index: 617

Text #15

Max Range: 2.5152. Min Range: -2.5152

Max Act: 1.7808. Min Act: -0.0000

Data Index: 306810 (C4 (Web Text))

Max Activating Token Index: 52

Text #16

Max Range: 2.5152. Min Range: -2.5152

Max Act: 1.7203. Min Act: -0.0000

Data Index: 229002 (C4 (Web Text))

Max Activating Token Index: 393

Text #17

Max Range: 2.5152. Min Range: -2.5152

Max Act: 1.5876. Min Act: -0.0000

Data Index: 876795 (C4 (Web Text))

Max Activating Token Index: 21

Text #18

Max Range: 2.5152. Min Range: -2.5152

Max Act: 1.5721. Min Act: -0.0000

Data Index: 314506 (C4 (Web Text))

Max Activating Token Index: 656

Text #19

Max Range: 2.5152. Min Range: -2.5152

Max Act: 1.6832. Min Act: -0.0000

Data Index: 470800 (C4 (Web Text))

Max Activating Token Index: 793