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

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

Neuron 2512 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8902. Min Range: -0.8902

Max Act: 0.8902. Min Act: -0.0002

Data Index: 1004264 (C4 (Web Text))

Max Activating Token Index: 576

Text #1

Max Range: 0.8902. Min Range: -0.8902

Max Act: 0.7507. Min Act: -0.0001

Data Index: 690965 (C4 (Web Text))

Max Activating Token Index: 759

Text #2

Max Range: 0.8902. Min Range: -0.8902

Max Act: 0.7925. Min Act: -0.0002

Data Index: 1002457 (C4 (Web Text))

Max Activating Token Index: 284

Text #3

Max Range: 0.8902. Min Range: -0.8902

Max Act: 0.7797. Min Act: -0.0001

Data Index: 573199 (C4 (Web Text))

Max Activating Token Index: 832

Text #4

Max Range: 0.8902. Min Range: -0.8902

Max Act: 0.6567. Min Act: -0.0001

Data Index: 1278594 (C4 (Web Text))

Max Activating Token Index: 59

Text #5

Max Range: 0.8902. Min Range: -0.8902

Max Act: 0.7197. Min Act: -0.0001

Data Index: 982001 (C4 (Web Text))

Max Activating Token Index: 644

Text #6

Max Range: 0.8902. Min Range: -0.8902

Max Act: 0.6570. Min Act: -0.0001

Data Index: 520133 (C4 (Web Text))

Max Activating Token Index: 98

Text #7

Max Range: 0.8902. Min Range: -0.8902

Max Act: 0.7186. Min Act: -0.0002

Data Index: 620917 (C4 (Web Text))

Max Activating Token Index: 1007

Text #8

Max Range: 0.8902. Min Range: -0.8902

Max Act: 0.7168. Min Act: -0.0002

Data Index: 495865 (C4 (Web Text))

Max Activating Token Index: 545

Text #9

Max Range: 0.8902. Min Range: -0.8902

Max Act: 0.6895. Min Act: -0.0002

Data Index: 385802 (C4 (Web Text))

Max Activating Token Index: 243

Text #10

Max Range: 0.8902. Min Range: -0.8902

Max Act: 0.6896. Min Act: -0.0002

Data Index: 774614 (C4 (Web Text))

Max Activating Token Index: 784

Text #11

Max Range: 0.8902. Min Range: -0.8902

Max Act: 0.6621. Min Act: -0.0001

Data Index: 687145 (C4 (Web Text))

Max Activating Token Index: 1013

Text #12

Max Range: 0.8902. Min Range: -0.8902

Max Act: 0.7444. Min Act: -0.0002

Data Index: 655157 (C4 (Web Text))

Max Activating Token Index: 317

Text #13

Max Range: 0.8902. Min Range: -0.8902

Max Act: 0.6220. Min Act: -0.0001

Data Index: 729261 (C4 (Web Text))

Max Activating Token Index: 76

Text #14

Max Range: 0.8902. Min Range: -0.8902

Max Act: 0.6379. Min Act: -0.0001

Data Index: 710842 (C4 (Web Text))

Max Activating Token Index: 959

Text #15

Max Range: 0.8902. Min Range: -0.8902

Max Act: 0.6542. Min Act: -0.0001

Data Index: 648874 (C4 (Web Text))

Max Activating Token Index: 239

Text #16

Max Range: 0.8902. Min Range: -0.8902

Max Act: 0.6592. Min Act: -0.0001

Data Index: 85966 (C4 (Web Text))

Max Activating Token Index: 724

Text #17

Max Range: 0.8902. Min Range: -0.8902

Max Act: 0.6612. Min Act: -0.0001

Data Index: 1300472 (C4 (Web Text))

Max Activating Token Index: 34

Text #18

Max Range: 0.8902. Min Range: -0.8902

Max Act: 0.6031. Min Act: -0.0002

Data Index: 308577 (C4 (Web Text))

Max Activating Token Index: 289

Text #19

Max Range: 0.8902. Min Range: -0.8902

Max Act: 0.6751. Min Act: -0.0001

Data Index: 701768 (C4 (Web Text))

Max Activating Token Index: 39