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

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

Neuron 3300 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: 0.0974. Min Range: -0.0974

Max Act: 0.0974. Min Act: -0.0003

Data Index: 59555 (C4 (Web Text))

Max Activating Token Index: 73

Text #1

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0907. Min Act: -0.0003

Data Index: 1003987 (C4 (Web Text))

Max Activating Token Index: 407

Text #2

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0808. Min Act: -0.0003

Data Index: 162551 (C4 (Web Text))

Max Activating Token Index: 661

Text #3

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0811. Min Act: -0.0003

Data Index: 810356 (C4 (Web Text))

Max Activating Token Index: 985

Text #4

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0863. Min Act: -0.0003

Data Index: 568953 (C4 (Web Text))

Max Activating Token Index: 762

Text #5

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0855. Min Act: -0.0003

Data Index: 1119043 (C4 (Web Text))

Max Activating Token Index: 426

Text #6

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0796. Min Act: -0.0003

Data Index: 1026418 (C4 (Web Text))

Max Activating Token Index: 793

Text #7

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0843. Min Act: -0.0003

Data Index: 174265 (C4 (Web Text))

Max Activating Token Index: 560

Text #8

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0831. Min Act: -0.0003

Data Index: 104518 (C4 (Web Text))

Max Activating Token Index: 808

Text #9

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0808. Min Act: -0.0003

Data Index: 1287793 (C4 (Web Text))

Max Activating Token Index: 881

Text #10

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0804. Min Act: -0.0003

Data Index: 632604 (C4 (Web Text))

Max Activating Token Index: 867

Text #11

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0802. Min Act: -0.0003

Data Index: 1334495 (C4 (Web Text))

Max Activating Token Index: 776

Text #12

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0771. Min Act: -0.0003

Data Index: 742982 (C4 (Web Text))

Max Activating Token Index: 438

Text #13

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0763. Min Act: -0.0003

Data Index: 372128 (C4 (Web Text))

Max Activating Token Index: 781

Text #14

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0729. Min Act: -0.0003

Data Index: 1083675 (C4 (Web Text))

Max Activating Token Index: 752

Text #15

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0807. Min Act: -0.0003

Data Index: 436532 (C4 (Web Text))

Max Activating Token Index: 969

Text #16

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0728. Min Act: -0.0003

Data Index: 732824 (C4 (Web Text))

Max Activating Token Index: 867

Text #17

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0847. Min Act: -0.0003

Data Index: 35752 (C4 (Web Text))

Max Activating Token Index: 593

Text #18

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0714. Min Act: -0.0003

Data Index: 478583 (C4 (Web Text))

Max Activating Token Index: 286

Text #19

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0683. Min Act: -0.0003

Data Index: 74695 (C4 (Web Text))

Max Activating Token Index: 792