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

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

Neuron 289 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.3806. Min Range: -1.3806

Max Act: 1.3806. Min Act: -0.0001

Data Index: 866597 (C4 (Web Text))

Max Activating Token Index: 329

Text #1

Max Range: 1.3806. Min Range: -1.3806

Max Act: 1.2940. Min Act: -0.0001

Data Index: 594348 (C4 (Web Text))

Max Activating Token Index: 957

Text #2

Max Range: 1.3806. Min Range: -1.3806

Max Act: 1.2469. Min Act: -0.0001

Data Index: 51320 (C4 (Web Text))

Max Activating Token Index: 636

Text #3

Max Range: 1.3806. Min Range: -1.3806

Max Act: 1.1564. Min Act: -0.0001

Data Index: 846963 (C4 (Web Text))

Max Activating Token Index: 246

Text #4

Max Range: 1.3806. Min Range: -1.3806

Max Act: 1.3141. Min Act: -0.0001

Data Index: 142256 (C4 (Web Text))

Max Activating Token Index: 823

Text #5

Max Range: 1.3806. Min Range: -1.3806

Max Act: 0.9855. Min Act: -0.0001

Data Index: 921222 (C4 (Web Text))

Max Activating Token Index: 785

Text #6

Max Range: 1.3806. Min Range: -1.3806

Max Act: 1.0767. Min Act: -0.0001

Data Index: 1182822 (C4 (Web Text))

Max Activating Token Index: 356

Text #7

Max Range: 1.3806. Min Range: -1.3806

Max Act: 1.0444. Min Act: -0.0001

Data Index: 1091778 (C4 (Web Text))

Max Activating Token Index: 558

Text #8

Max Range: 1.3806. Min Range: -1.3806

Max Act: 1.0337. Min Act: -0.0001

Data Index: 57374 (C4 (Web Text))

Max Activating Token Index: 470

Text #9

Max Range: 1.3806. Min Range: -1.3806

Max Act: 0.9999. Min Act: -0.0001

Data Index: 533130 (C4 (Web Text))

Max Activating Token Index: 42

Text #10

Max Range: 1.3806. Min Range: -1.3806

Max Act: 1.0182. Min Act: -0.0001

Data Index: 96810 (C4 (Web Text))

Max Activating Token Index: 974

Text #11

Max Range: 1.3806. Min Range: -1.3806

Max Act: 0.9555. Min Act: -0.0001

Data Index: 381773 (C4 (Web Text))

Max Activating Token Index: 661

Text #12

Max Range: 1.3806. Min Range: -1.3806

Max Act: 0.9581. Min Act: -0.0001

Data Index: 440718 (C4 (Web Text))

Max Activating Token Index: 821

Text #13

Max Range: 1.3806. Min Range: -1.3806

Max Act: 0.8728. Min Act: -0.0001

Data Index: 152001 (C4 (Web Text))

Max Activating Token Index: 143

Text #14

Max Range: 1.3806. Min Range: -1.3806

Max Act: 0.8644. Min Act: -0.0001

Data Index: 257596 (C4 (Web Text))

Max Activating Token Index: 687

Text #15

Max Range: 1.3806. Min Range: -1.3806

Max Act: 0.8592. Min Act: -0.0001

Data Index: 301737 (C4 (Web Text))

Max Activating Token Index: 381

Text #16

Max Range: 1.3806. Min Range: -1.3806

Max Act: 0.9159. Min Act: -0.0001

Data Index: 854291 (C4 (Web Text))

Max Activating Token Index: 670

Text #17

Max Range: 1.3806. Min Range: -1.3806

Max Act: 0.8732. Min Act: -0.0001

Data Index: 1007805 (C4 (Web Text))

Max Activating Token Index: 804

Text #18

Max Range: 1.3806. Min Range: -1.3806

Max Act: 0.8953. Min Act: -0.0001

Data Index: 551720 (C4 (Web Text))

Max Activating Token Index: 743

Text #19

Max Range: 1.3806. Min Range: -1.3806

Max Act: 0.8696. Min Act: -0.0001

Data Index: 602903 (C4 (Web Text))

Max Activating Token Index: 218