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

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

Neuron 4147 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.8696. Min Range: -4.8696

Max Act: 4.8696. Min Act: -0.0000

Data Index: 369720 (C4 (Web Text))

Max Activating Token Index: 677

Text #1

Max Range: 4.8696. Min Range: -4.8696

Max Act: 4.7326. Min Act: -0.0000

Data Index: 945047 (C4 (Web Text))

Max Activating Token Index: 910

Text #2

Max Range: 4.8696. Min Range: -4.8696

Max Act: 4.0217. Min Act: -0.0000

Data Index: 1033143 (C4 (Web Text))

Max Activating Token Index: 358

Text #3

Max Range: 4.8696. Min Range: -4.8696

Max Act: 3.9378. Min Act: -0.0000

Data Index: 71015 (C4 (Web Text))

Max Activating Token Index: 261

Text #4

Max Range: 4.8696. Min Range: -4.8696

Max Act: 3.9573. Min Act: -0.0000

Data Index: 1355636 (C4 (Web Text))

Max Activating Token Index: 857

Text #5

Max Range: 4.8696. Min Range: -4.8696

Max Act: 3.8995. Min Act: -0.0000

Data Index: 387387 (C4 (Web Text))

Max Activating Token Index: 647

Text #6

Max Range: 4.8696. Min Range: -4.8696

Max Act: 3.6122. Min Act: -0.0000

Data Index: 947088 (C4 (Web Text))

Max Activating Token Index: 813

Text #7

Max Range: 4.8696. Min Range: -4.8696

Max Act: 3.3704. Min Act: -0.0000

Data Index: 1650071 (Python Code)

Max Activating Token Index: 881

Text #8

Max Range: 4.8696. Min Range: -4.8696

Max Act: 3.3762. Min Act: -0.0000

Data Index: 1071085 (C4 (Web Text))

Max Activating Token Index: 265

Text #9

Max Range: 4.8696. Min Range: -4.8696

Max Act: 3.1804. Min Act: -0.0000

Data Index: 1182944 (C4 (Web Text))

Max Activating Token Index: 827

Text #10

Max Range: 4.8696. Min Range: -4.8696

Max Act: 3.3123. Min Act: -0.0000

Data Index: 1577632 (Python Code)

Max Activating Token Index: 746

Text #11

Max Range: 4.8696. Min Range: -4.8696

Max Act: 3.1264. Min Act: -0.0000

Data Index: 1397916 (Python Code)

Max Activating Token Index: 584

Text #12

Max Range: 4.8696. Min Range: -4.8696

Max Act: 2.7903. Min Act: -0.0000

Data Index: 463788 (C4 (Web Text))

Max Activating Token Index: 84

Text #13

Max Range: 4.8696. Min Range: -4.8696

Max Act: 2.8704. Min Act: -0.0000

Data Index: 270870 (C4 (Web Text))

Max Activating Token Index: 557

Text #14

Max Range: 4.8696. Min Range: -4.8696

Max Act: 2.9900. Min Act: -0.0000

Data Index: 886480 (C4 (Web Text))

Max Activating Token Index: 982

Text #15

Max Range: 4.8696. Min Range: -4.8696

Max Act: 3.0810. Min Act: -0.0000

Data Index: 757353 (C4 (Web Text))

Max Activating Token Index: 859

Text #16

Max Range: 4.8696. Min Range: -4.8696

Max Act: 2.9333. Min Act: -0.0000

Data Index: 297678 (C4 (Web Text))

Max Activating Token Index: 901

Text #17

Max Range: 4.8696. Min Range: -4.8696

Max Act: 2.9365. Min Act: -0.0000

Data Index: 134805 (C4 (Web Text))

Max Activating Token Index: 654

Text #18

Max Range: 4.8696. Min Range: -4.8696

Max Act: 2.7505. Min Act: -0.0000

Data Index: 1415708 (Python Code)

Max Activating Token Index: 809

Text #19

Max Range: 4.8696. Min Range: -4.8696

Max Act: 2.9944. Min Act: -0.0000

Data Index: 39135 (C4 (Web Text))

Max Activating Token Index: 960