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

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

Neuron 2799 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: 0.4561. Min Range: -0.4561

Max Act: 0.4561. Min Act: -0.0001

Data Index: 335952 (C4 (Web Text))

Max Activating Token Index: 301

Text #1

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.4261. Min Act: -0.0001

Data Index: 1348738 (C4 (Web Text))

Max Activating Token Index: 295

Text #2

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.3796. Min Act: -0.0001

Data Index: 1008957 (C4 (Web Text))

Max Activating Token Index: 678

Text #3

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.3299. Min Act: -0.0001

Data Index: 830019 (C4 (Web Text))

Max Activating Token Index: 59

Text #4

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.3488. Min Act: -0.0001

Data Index: 1337815 (C4 (Web Text))

Max Activating Token Index: 881

Text #5

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.3055. Min Act: -0.0001

Data Index: 205746 (C4 (Web Text))

Max Activating Token Index: 69

Text #6

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.3023. Min Act: -0.0001

Data Index: 703595 (C4 (Web Text))

Max Activating Token Index: 93

Text #7

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.2795. Min Act: -0.0001

Data Index: 739766 (C4 (Web Text))

Max Activating Token Index: 924

Text #8

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.2888. Min Act: -0.0001

Data Index: 1172600 (C4 (Web Text))

Max Activating Token Index: 410

Text #9

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.2607. Min Act: -0.0001

Data Index: 274911 (C4 (Web Text))

Max Activating Token Index: 440

Text #10

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.2699. Min Act: -0.0001

Data Index: 837361 (C4 (Web Text))

Max Activating Token Index: 826

Text #11

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.2421. Min Act: -0.0002

Data Index: 1291695 (C4 (Web Text))

Max Activating Token Index: 664

Text #12

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.2628. Min Act: -0.0001

Data Index: 148136 (C4 (Web Text))

Max Activating Token Index: 361

Text #13

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.3046. Min Act: -0.0001

Data Index: 503869 (C4 (Web Text))

Max Activating Token Index: 335

Text #14

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.2925. Min Act: -0.0001

Data Index: 113638 (C4 (Web Text))

Max Activating Token Index: 356

Text #15

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.2388. Min Act: -0.0002

Data Index: 153473 (C4 (Web Text))

Max Activating Token Index: 249

Text #16

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.2791. Min Act: -0.0001

Data Index: 735147 (C4 (Web Text))

Max Activating Token Index: 933

Text #17

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.2584. Min Act: -0.0001

Data Index: 805782 (C4 (Web Text))

Max Activating Token Index: 985

Text #18

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.2486. Min Act: -0.0001

Data Index: 1203031 (C4 (Web Text))

Max Activating Token Index: 781

Text #19

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.2649. Min Act: -0.0001

Data Index: 432704 (C4 (Web Text))

Max Activating Token Index: 616