Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3943 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5762. Min Range: -0.5762

Max Act: 0.5762. Min Act: -0.0000

Data Index: 165625 (C4 (Web Text))

Max Activating Token Index: 65

Text #1

Max Range: 0.5762. Min Range: -0.5762

Max Act: 0.5595. Min Act: -0.0000

Data Index: 999679 (C4 (Web Text))

Max Activating Token Index: 752

Text #2

Max Range: 0.5762. Min Range: -0.5762

Max Act: 0.5116. Min Act: -0.0000

Data Index: 279993 (C4 (Web Text))

Max Activating Token Index: 689

Text #3

Max Range: 0.5762. Min Range: -0.5762

Max Act: 0.4867. Min Act: -0.0000

Data Index: 931477 (C4 (Web Text))

Max Activating Token Index: 123

Text #4

Max Range: 0.5762. Min Range: -0.5762

Max Act: 0.4938. Min Act: -0.0000

Data Index: 1120209 (C4 (Web Text))

Max Activating Token Index: 221

Text #5

Max Range: 0.5762. Min Range: -0.5762

Max Act: 0.5004. Min Act: -0.0000

Data Index: 65025 (C4 (Web Text))

Max Activating Token Index: 542

Text #6

Max Range: 0.5762. Min Range: -0.5762

Max Act: 0.4919. Min Act: -0.0000

Data Index: 823681 (C4 (Web Text))

Max Activating Token Index: 445

Text #7

Max Range: 0.5762. Min Range: -0.5762

Max Act: 0.4916. Min Act: -0.0000

Data Index: 1030096 (C4 (Web Text))

Max Activating Token Index: 24

Text #8

Max Range: 0.5762. Min Range: -0.5762

Max Act: 0.4781. Min Act: -0.0000

Data Index: 1300619 (C4 (Web Text))

Max Activating Token Index: 701

Text #9

Max Range: 0.5762. Min Range: -0.5762

Max Act: 0.4664. Min Act: -0.0000

Data Index: 1226939 (C4 (Web Text))

Max Activating Token Index: 596

Text #10

Max Range: 0.5762. Min Range: -0.5762

Max Act: 0.4973. Min Act: -0.0000

Data Index: 554456 (C4 (Web Text))

Max Activating Token Index: 981

Text #11

Max Range: 0.5762. Min Range: -0.5762

Max Act: 0.4793. Min Act: -0.0000

Data Index: 180349 (C4 (Web Text))

Max Activating Token Index: 358

Text #12

Max Range: 0.5762. Min Range: -0.5762

Max Act: 0.4743. Min Act: -0.0000

Data Index: 1130596 (C4 (Web Text))

Max Activating Token Index: 610

Text #13

Max Range: 0.5762. Min Range: -0.5762

Max Act: 0.4475. Min Act: -0.0000

Data Index: 1070663 (C4 (Web Text))

Max Activating Token Index: 395

Text #14

Max Range: 0.5762. Min Range: -0.5762

Max Act: 0.4422. Min Act: -0.0000

Data Index: 1022141 (C4 (Web Text))

Max Activating Token Index: 772

Text #15

Max Range: 0.5762. Min Range: -0.5762

Max Act: 0.4588. Min Act: -0.0000

Data Index: 614766 (C4 (Web Text))

Max Activating Token Index: 47

Text #16

Max Range: 0.5762. Min Range: -0.5762

Max Act: 0.4387. Min Act: -0.0000

Data Index: 329326 (C4 (Web Text))

Max Activating Token Index: 75

Text #17

Max Range: 0.5762. Min Range: -0.5762

Max Act: 0.4677. Min Act: -0.0000

Data Index: 50733 (C4 (Web Text))

Max Activating Token Index: 665

Text #18

Max Range: 0.5762. Min Range: -0.5762

Max Act: 0.4516. Min Act: -0.0000

Data Index: 1253317 (C4 (Web Text))

Max Activating Token Index: 182

Text #19

Max Range: 0.5762. Min Range: -0.5762

Max Act: 0.4527. Min Act: -0.0000

Data Index: 698257 (C4 (Web Text))

Max Activating Token Index: 49