Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 911 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0902. Min Range: -1.0902

Max Act: 1.0902. Min Act: -0.0001

Data Index: 137899 (C4 (Web Text))

Max Activating Token Index: 772

Text #1

Max Range: 1.0902. Min Range: -1.0902

Max Act: 0.9604. Min Act: -0.0000

Data Index: 368571 (C4 (Web Text))

Max Activating Token Index: 761

Text #2

Max Range: 1.0902. Min Range: -1.0902

Max Act: 0.9663. Min Act: -0.0001

Data Index: 72193 (C4 (Web Text))

Max Activating Token Index: 913

Text #3

Max Range: 1.0902. Min Range: -1.0902

Max Act: 0.9588. Min Act: -0.0001

Data Index: 216894 (C4 (Web Text))

Max Activating Token Index: 312

Text #4

Max Range: 1.0902. Min Range: -1.0902

Max Act: 0.9123. Min Act: -0.0001

Data Index: 990142 (C4 (Web Text))

Max Activating Token Index: 728

Text #5

Max Range: 1.0902. Min Range: -1.0902

Max Act: 0.8759. Min Act: -0.0000

Data Index: 923419 (C4 (Web Text))

Max Activating Token Index: 690

Text #6

Max Range: 1.0902. Min Range: -1.0902

Max Act: 0.9434. Min Act: -0.0000

Data Index: 1210988 (C4 (Web Text))

Max Activating Token Index: 912

Text #7

Max Range: 1.0902. Min Range: -1.0902

Max Act: 0.9444. Min Act: -0.0001

Data Index: 998054 (C4 (Web Text))

Max Activating Token Index: 45

Text #8

Max Range: 1.0902. Min Range: -1.0902

Max Act: 0.9177. Min Act: -0.0001

Data Index: 766608 (C4 (Web Text))

Max Activating Token Index: 266

Text #9

Max Range: 1.0902. Min Range: -1.0902

Max Act: 0.9404. Min Act: -0.0000

Data Index: 318152 (C4 (Web Text))

Max Activating Token Index: 880

Text #10

Max Range: 1.0902. Min Range: -1.0902

Max Act: 0.8714. Min Act: -0.0001

Data Index: 552877 (C4 (Web Text))

Max Activating Token Index: 280

Text #11

Max Range: 1.0902. Min Range: -1.0902

Max Act: 0.8656. Min Act: -0.0001

Data Index: 359570 (C4 (Web Text))

Max Activating Token Index: 1019

Text #12

Max Range: 1.0902. Min Range: -1.0902

Max Act: 0.8884. Min Act: -0.0001

Data Index: 1179357 (C4 (Web Text))

Max Activating Token Index: 677

Text #13

Max Range: 1.0902. Min Range: -1.0902

Max Act: 0.8862. Min Act: -0.0000

Data Index: 122511 (C4 (Web Text))

Max Activating Token Index: 946

Text #14

Max Range: 1.0902. Min Range: -1.0902

Max Act: 0.8594. Min Act: -0.0000

Data Index: 1348693 (C4 (Web Text))

Max Activating Token Index: 681

Text #15

Max Range: 1.0902. Min Range: -1.0902

Max Act: 0.8808. Min Act: -0.0001

Data Index: 1213557 (C4 (Web Text))

Max Activating Token Index: 43

Text #16

Max Range: 1.0902. Min Range: -1.0902

Max Act: 0.8596. Min Act: -0.0000

Data Index: 1453175 (Python Code)

Max Activating Token Index: 797

Text #17

Max Range: 1.0902. Min Range: -1.0902

Max Act: 0.8827. Min Act: -0.0000

Data Index: 66442 (C4 (Web Text))

Max Activating Token Index: 490

Text #18

Max Range: 1.0902. Min Range: -1.0902

Max Act: 0.8714. Min Act: -0.0001

Data Index: 781859 (C4 (Web Text))

Max Activating Token Index: 217

Text #19

Max Range: 1.0902. Min Range: -1.0902

Max Act: 0.8979. Min Act: -0.0001

Data Index: 767851 (C4 (Web Text))

Max Activating Token Index: 125