Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 912 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.5841. Min Range: -1.5841

Max Act: 1.5841. Min Act: -0.0001

Data Index: 986321 (C4 (Web Text))

Max Activating Token Index: 950

Text #1

Max Range: 1.5841. Min Range: -1.5841

Max Act: 1.3540. Min Act: -0.0001

Data Index: 984623 (C4 (Web Text))

Max Activating Token Index: 646

Text #2

Max Range: 1.5841. Min Range: -1.5841

Max Act: 1.2543. Min Act: -0.0001

Data Index: 566417 (C4 (Web Text))

Max Activating Token Index: 947

Text #3

Max Range: 1.5841. Min Range: -1.5841

Max Act: 0.9811. Min Act: -0.0001

Data Index: 879641 (C4 (Web Text))

Max Activating Token Index: 66

Text #4

Max Range: 1.5841. Min Range: -1.5841

Max Act: 0.9568. Min Act: -0.0001

Data Index: 1328764 (C4 (Web Text))

Max Activating Token Index: 936

Text #5

Max Range: 1.5841. Min Range: -1.5841

Max Act: 0.9822. Min Act: -0.0001

Data Index: 759772 (C4 (Web Text))

Max Activating Token Index: 277

Text #6

Max Range: 1.5841. Min Range: -1.5841

Max Act: 0.8715. Min Act: -0.0001

Data Index: 1089045 (C4 (Web Text))

Max Activating Token Index: 983

Text #7

Max Range: 1.5841. Min Range: -1.5841

Max Act: 0.9702. Min Act: -0.0001

Data Index: 930341 (C4 (Web Text))

Max Activating Token Index: 234

Text #8

Max Range: 1.5841. Min Range: -1.5841

Max Act: 0.8819. Min Act: -0.0001

Data Index: 671185 (C4 (Web Text))

Max Activating Token Index: 73

Text #9

Max Range: 1.5841. Min Range: -1.5841

Max Act: 0.8892. Min Act: -0.0001

Data Index: 443203 (C4 (Web Text))

Max Activating Token Index: 642

Text #10

Max Range: 1.5841. Min Range: -1.5841

Max Act: 0.9413. Min Act: -0.0001

Data Index: 643343 (C4 (Web Text))

Max Activating Token Index: 881

Text #11

Max Range: 1.5841. Min Range: -1.5841

Max Act: 0.9023. Min Act: -0.0001

Data Index: 195311 (C4 (Web Text))

Max Activating Token Index: 214

Text #12

Max Range: 1.5841. Min Range: -1.5841

Max Act: 0.9025. Min Act: -0.0001

Data Index: 920954 (C4 (Web Text))

Max Activating Token Index: 492

Text #13

Max Range: 1.5841. Min Range: -1.5841

Max Act: 0.8842. Min Act: -0.0001

Data Index: 739666 (C4 (Web Text))

Max Activating Token Index: 543

Text #14

Max Range: 1.5841. Min Range: -1.5841

Max Act: 0.8932. Min Act: -0.0001

Data Index: 386641 (C4 (Web Text))

Max Activating Token Index: 973

Text #15

Max Range: 1.5841. Min Range: -1.5841

Max Act: 0.8602. Min Act: -0.0001

Data Index: 92271 (C4 (Web Text))

Max Activating Token Index: 172

Text #16

Max Range: 1.5841. Min Range: -1.5841

Max Act: 0.8107. Min Act: -0.0002

Data Index: 99454 (C4 (Web Text))

Max Activating Token Index: 679

Text #17

Max Range: 1.5841. Min Range: -1.5841

Max Act: 0.9120. Min Act: -0.0001

Data Index: 468559 (C4 (Web Text))

Max Activating Token Index: 606

Text #18

Max Range: 1.5841. Min Range: -1.5841

Max Act: 0.8773. Min Act: -0.0001

Data Index: 102033 (C4 (Web Text))

Max Activating Token Index: 56

Text #19

Max Range: 1.5841. Min Range: -1.5841

Max Act: 0.8612. Min Act: -0.0001

Data Index: 833297 (C4 (Web Text))

Max Activating Token Index: 275