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

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

Neuron 581 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0994. Min Act: -0.0001

Data Index: 5046 (C4 (Web Text))

Max Activating Token Index: 897

Text #1

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0981. Min Act: -0.0001

Data Index: 1321366 (C4 (Web Text))

Max Activating Token Index: 422

Text #2

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0998. Min Act: -0.0001

Data Index: 126622 (C4 (Web Text))

Max Activating Token Index: 500

Text #3

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0849. Min Act: -0.0001

Data Index: 1119013 (C4 (Web Text))

Max Activating Token Index: 72

Text #4

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0982. Min Act: -0.0001

Data Index: 1174310 (C4 (Web Text))

Max Activating Token Index: 305

Text #5

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0897. Min Act: -0.0001

Data Index: 1018409 (C4 (Web Text))

Max Activating Token Index: 513

Text #6

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0853. Min Act: -0.0001

Data Index: 1431625 (Python Code)

Max Activating Token Index: 827

Text #7

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0794. Min Act: -0.0001

Data Index: 1200760 (C4 (Web Text))

Max Activating Token Index: 881

Text #8

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0817. Min Act: -0.0001

Data Index: 63864 (C4 (Web Text))

Max Activating Token Index: 331

Text #9

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0815. Min Act: -0.0001

Data Index: 1122801 (C4 (Web Text))

Max Activating Token Index: 328

Text #10

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0807. Min Act: -0.0001

Data Index: 785982 (C4 (Web Text))

Max Activating Token Index: 994

Text #11

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0843. Min Act: -0.0001

Data Index: 287156 (C4 (Web Text))

Max Activating Token Index: 521

Text #12

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0841. Min Act: -0.0001

Data Index: 1306004 (C4 (Web Text))

Max Activating Token Index: 384

Text #13

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0795. Min Act: -0.0001

Data Index: 71864 (C4 (Web Text))

Max Activating Token Index: 592

Text #14

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0824. Min Act: -0.0001

Data Index: 811454 (C4 (Web Text))

Max Activating Token Index: 533

Text #15

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0822. Min Act: -0.0001

Data Index: 834661 (C4 (Web Text))

Max Activating Token Index: 167

Text #16

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0838. Min Act: -0.0001

Data Index: 536723 (C4 (Web Text))

Max Activating Token Index: 228

Text #17

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0908. Min Act: -0.0001

Data Index: 311297 (C4 (Web Text))

Max Activating Token Index: 929

Text #18

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0808. Min Act: -0.0001

Data Index: 207628 (C4 (Web Text))

Max Activating Token Index: 769

Text #19

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0866. Min Act: -0.0001

Data Index: 1176277 (C4 (Web Text))

Max Activating Token Index: 155