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

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

Neuron 1000 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0838. Min Act: -0.0003

Data Index: 740308 (C4 (Web Text))

Max Activating Token Index: 913

Text #1

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0935. Min Act: -0.0003

Data Index: 69629 (C4 (Web Text))

Max Activating Token Index: 141

Text #2

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0828. Min Act: -0.0003

Data Index: 1353207 (C4 (Web Text))

Max Activating Token Index: 188

Text #3

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0866. Min Act: -0.0003

Data Index: 589585 (C4 (Web Text))

Max Activating Token Index: 401

Text #4

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0846. Min Act: -0.0003

Data Index: 703821 (C4 (Web Text))

Max Activating Token Index: 1012

Text #5

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0879. Min Act: -0.0003

Data Index: 206966 (C4 (Web Text))

Max Activating Token Index: 434

Text #6

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0912. Min Act: -0.0003

Data Index: 28894 (C4 (Web Text))

Max Activating Token Index: 277

Text #7

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0785. Min Act: -0.0003

Data Index: 464364 (C4 (Web Text))

Max Activating Token Index: 807

Text #8

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0804. Min Act: -0.0003

Data Index: 464602 (C4 (Web Text))

Max Activating Token Index: 753

Text #9

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0864. Min Act: -0.0003

Data Index: 546478 (C4 (Web Text))

Max Activating Token Index: 986

Text #10

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0864. Min Act: -0.0003

Data Index: 753478 (C4 (Web Text))

Max Activating Token Index: 922

Text #11

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0888. Min Act: -0.0003

Data Index: 629597 (C4 (Web Text))

Max Activating Token Index: 1017

Text #12

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0875. Min Act: -0.0003

Data Index: 643871 (C4 (Web Text))

Max Activating Token Index: 357

Text #13

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0816. Min Act: -0.0003

Data Index: 747850 (C4 (Web Text))

Max Activating Token Index: 642

Text #14

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0875. Min Act: -0.0004

Data Index: 72849 (C4 (Web Text))

Max Activating Token Index: 62

Text #15

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0833. Min Act: -0.0003

Data Index: 320815 (C4 (Web Text))

Max Activating Token Index: 908

Text #16

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0828. Min Act: -0.0003

Data Index: 111738 (C4 (Web Text))

Max Activating Token Index: 125

Text #17

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0821. Min Act: -0.0003

Data Index: 1189689 (C4 (Web Text))

Max Activating Token Index: 76

Text #18

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0821. Min Act: -0.0003

Data Index: 1252857 (C4 (Web Text))

Max Activating Token Index: 280

Text #19

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0786. Min Act: -0.0003

Data Index: 663390 (C4 (Web Text))

Max Activating Token Index: 820