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

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

Neuron 4287 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: 1.0941. Min Range: -1.0941

Max Act: 1.0941. Min Act: -0.0000

Data Index: 973715 (C4 (Web Text))

Max Activating Token Index: 681

Text #1

Max Range: 1.0941. Min Range: -1.0941

Max Act: 0.9634. Min Act: -0.0000

Data Index: 802626 (C4 (Web Text))

Max Activating Token Index: 1022

Text #2

Max Range: 1.0941. Min Range: -1.0941

Max Act: 0.8406. Min Act: -0.0000

Data Index: 620596 (C4 (Web Text))

Max Activating Token Index: 718

Text #3

Max Range: 1.0941. Min Range: -1.0941

Max Act: 0.7506. Min Act: -0.0000

Data Index: 1230246 (C4 (Web Text))

Max Activating Token Index: 312

Text #4

Max Range: 1.0941. Min Range: -1.0941

Max Act: 0.6876. Min Act: -0.0000

Data Index: 72065 (C4 (Web Text))

Max Activating Token Index: 33

Text #5

Max Range: 1.0941. Min Range: -1.0941

Max Act: 0.6931. Min Act: -0.0000

Data Index: 308299 (C4 (Web Text))

Max Activating Token Index: 813

Text #6

Max Range: 1.0941. Min Range: -1.0941

Max Act: 0.6590. Min Act: -0.0000

Data Index: 581155 (C4 (Web Text))

Max Activating Token Index: 337

Text #7

Max Range: 1.0941. Min Range: -1.0941

Max Act: 0.6484. Min Act: -0.0000

Data Index: 495480 (C4 (Web Text))

Max Activating Token Index: 893

Text #8

Max Range: 1.0941. Min Range: -1.0941

Max Act: 0.6675. Min Act: -0.0000

Data Index: 695373 (C4 (Web Text))

Max Activating Token Index: 703

Text #9

Max Range: 1.0941. Min Range: -1.0941

Max Act: 0.6103. Min Act: -0.0000

Data Index: 1077237 (C4 (Web Text))

Max Activating Token Index: 911

Text #10

Max Range: 1.0941. Min Range: -1.0941

Max Act: 0.6038. Min Act: -0.0000

Data Index: 783618 (C4 (Web Text))

Max Activating Token Index: 752

Text #11

Max Range: 1.0941. Min Range: -1.0941

Max Act: 0.5976. Min Act: -0.0000

Data Index: 747859 (C4 (Web Text))

Max Activating Token Index: 564

Text #12

Max Range: 1.0941. Min Range: -1.0941

Max Act: 0.5569. Min Act: -0.0000

Data Index: 595238 (C4 (Web Text))

Max Activating Token Index: 832

Text #13

Max Range: 1.0941. Min Range: -1.0941

Max Act: 0.5634. Min Act: -0.0000

Data Index: 678046 (C4 (Web Text))

Max Activating Token Index: 783

Text #14

Max Range: 1.0941. Min Range: -1.0941

Max Act: 0.5277. Min Act: -0.0000

Data Index: 623071 (C4 (Web Text))

Max Activating Token Index: 77

Text #15

Max Range: 1.0941. Min Range: -1.0941

Max Act: 0.5155. Min Act: -0.0000

Data Index: 1116554 (C4 (Web Text))

Max Activating Token Index: 907

Text #16

Max Range: 1.0941. Min Range: -1.0941

Max Act: 0.5284. Min Act: -0.0000

Data Index: 218484 (C4 (Web Text))

Max Activating Token Index: 363

Text #17

Max Range: 1.0941. Min Range: -1.0941

Max Act: 0.4794. Min Act: -0.0000

Data Index: 1068982 (C4 (Web Text))

Max Activating Token Index: 519

Text #18

Max Range: 1.0941. Min Range: -1.0941

Max Act: 0.5167. Min Act: -0.0000

Data Index: 228438 (C4 (Web Text))

Max Activating Token Index: 872

Text #19

Max Range: 1.0941. Min Range: -1.0941

Max Act: 0.5026. Min Act: -0.0000

Data Index: 422280 (C4 (Web Text))

Max Activating Token Index: 457