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

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

Neuron 4856 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: 0.4663. Min Range: -0.4663

Max Act: 0.4663. Min Act: -0.0000

Data Index: 907728 (C4 (Web Text))

Max Activating Token Index: 33

Text #1

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.4454. Min Act: -0.0000

Data Index: 1030375 (C4 (Web Text))

Max Activating Token Index: 388

Text #2

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.4395. Min Act: -0.0000

Data Index: 1182039 (C4 (Web Text))

Max Activating Token Index: 669

Text #3

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.4258. Min Act: -0.0000

Data Index: 968508 (C4 (Web Text))

Max Activating Token Index: 304

Text #4

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3937. Min Act: -0.0000

Data Index: 31995 (C4 (Web Text))

Max Activating Token Index: 285

Text #5

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3908. Min Act: -0.0000

Data Index: 257199 (C4 (Web Text))

Max Activating Token Index: 573

Text #6

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3986. Min Act: -0.0000

Data Index: 1129893 (C4 (Web Text))

Max Activating Token Index: 62

Text #7

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3853. Min Act: -0.0000

Data Index: 1207521 (C4 (Web Text))

Max Activating Token Index: 379

Text #8

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3962. Min Act: -0.0000

Data Index: 117022 (C4 (Web Text))

Max Activating Token Index: 440

Text #9

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3943. Min Act: -0.0000

Data Index: 95462 (C4 (Web Text))

Max Activating Token Index: 747

Text #10

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3946. Min Act: -0.0000

Data Index: 953588 (C4 (Web Text))

Max Activating Token Index: 974

Text #11

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3962. Min Act: -0.0000

Data Index: 94700 (C4 (Web Text))

Max Activating Token Index: 628

Text #12

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.4223. Min Act: -0.0000

Data Index: 1323234 (C4 (Web Text))

Max Activating Token Index: 563

Text #13

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3895. Min Act: -0.0000

Data Index: 955086 (C4 (Web Text))

Max Activating Token Index: 487

Text #14

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3786. Min Act: -0.0000

Data Index: 684498 (C4 (Web Text))

Max Activating Token Index: 751

Text #15

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3643. Min Act: -0.0000

Data Index: 92435 (C4 (Web Text))

Max Activating Token Index: 1011

Text #16

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3713. Min Act: -0.0000

Data Index: 872756 (C4 (Web Text))

Max Activating Token Index: 104

Text #17

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3669. Min Act: -0.0000

Data Index: 652834 (C4 (Web Text))

Max Activating Token Index: 712

Text #18

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3627. Min Act: -0.0000

Data Index: 757464 (C4 (Web Text))

Max Activating Token Index: 197

Text #19

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3600. Min Act: -0.0000

Data Index: 564877 (C4 (Web Text))

Max Activating Token Index: 895