Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1818 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0925. Min Act: -0.0006

Data Index: 615231 (C4 (Web Text))

Max Activating Token Index: 590

Text #1

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0825. Min Act: -0.0006

Data Index: 1273012 (C4 (Web Text))

Max Activating Token Index: 102

Text #2

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0845. Min Act: -0.0006

Data Index: 602680 (C4 (Web Text))

Max Activating Token Index: 615

Text #3

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0795. Min Act: -0.0006

Data Index: 928519 (C4 (Web Text))

Max Activating Token Index: 756

Text #4

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0792. Min Act: -0.0006

Data Index: 1228503 (C4 (Web Text))

Max Activating Token Index: 488

Text #5

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0783. Min Act: -0.0006

Data Index: 907187 (C4 (Web Text))

Max Activating Token Index: 588

Text #6

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0807. Min Act: -0.0006

Data Index: 165222 (C4 (Web Text))

Max Activating Token Index: 316

Text #7

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0744. Min Act: -0.0005

Data Index: 1181933 (C4 (Web Text))

Max Activating Token Index: 438

Text #8

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0767. Min Act: -0.0006

Data Index: 858712 (C4 (Web Text))

Max Activating Token Index: 151

Text #9

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0749. Min Act: -0.0006

Data Index: 271061 (C4 (Web Text))

Max Activating Token Index: 216

Text #10

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0762. Min Act: -0.0006

Data Index: 482237 (C4 (Web Text))

Max Activating Token Index: 435

Text #11

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0742. Min Act: -0.0006

Data Index: 1098479 (C4 (Web Text))

Max Activating Token Index: 885

Text #12

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0684. Min Act: -0.0006

Data Index: 833409 (C4 (Web Text))

Max Activating Token Index: 982

Text #13

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0742. Min Act: -0.0006

Data Index: 676922 (C4 (Web Text))

Max Activating Token Index: 530

Text #14

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0729. Min Act: -0.0006

Data Index: 947132 (C4 (Web Text))

Max Activating Token Index: 530

Text #15

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0773. Min Act: -0.0006

Data Index: 708723 (C4 (Web Text))

Max Activating Token Index: 364

Text #16

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0757. Min Act: -0.0006

Data Index: 553996 (C4 (Web Text))

Max Activating Token Index: 889

Text #17

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0727. Min Act: -0.0005

Data Index: 402736 (C4 (Web Text))

Max Activating Token Index: 372

Text #18

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0739. Min Act: -0.0006

Data Index: 742560 (C4 (Web Text))

Max Activating Token Index: 328

Text #19

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0741. Min Act: -0.0006

Data Index: 172623 (C4 (Web Text))

Max Activating Token Index: 707