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

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

Neuron 2040 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.4954. Min Range: -2.4954

Max Act: 2.4954. Min Act: -0.0000

Data Index: 157644 (C4 (Web Text))

Max Activating Token Index: 331

Text #1

Max Range: 2.4954. Min Range: -2.4954

Max Act: 1.2704. Min Act: -0.0000

Data Index: 834313 (C4 (Web Text))

Max Activating Token Index: 495

Text #2

Max Range: 2.4954. Min Range: -2.4954

Max Act: 1.2923. Min Act: -0.0000

Data Index: 687451 (C4 (Web Text))

Max Activating Token Index: 340

Text #3

Max Range: 2.4954. Min Range: -2.4954

Max Act: 1.2753. Min Act: -0.0000

Data Index: 567600 (C4 (Web Text))

Max Activating Token Index: 385

Text #4

Max Range: 2.4954. Min Range: -2.4954

Max Act: 1.1810. Min Act: -0.0000

Data Index: 268279 (C4 (Web Text))

Max Activating Token Index: 574

Text #5

Max Range: 2.4954. Min Range: -2.4954

Max Act: 1.2109. Min Act: -0.0000

Data Index: 486498 (C4 (Web Text))

Max Activating Token Index: 338

Text #6

Max Range: 2.4954. Min Range: -2.4954

Max Act: 1.2660. Min Act: -0.0000

Data Index: 1286677 (C4 (Web Text))

Max Activating Token Index: 39

Text #7

Max Range: 2.4954. Min Range: -2.4954

Max Act: 1.2528. Min Act: -0.0000

Data Index: 1230783 (C4 (Web Text))

Max Activating Token Index: 210

Text #8

Max Range: 2.4954. Min Range: -2.4954

Max Act: 1.1472. Min Act: -0.0000

Data Index: 299412 (C4 (Web Text))

Max Activating Token Index: 594

Text #9

Max Range: 2.4954. Min Range: -2.4954

Max Act: 1.0731. Min Act: -0.0000

Data Index: 784758 (C4 (Web Text))

Max Activating Token Index: 735

Text #10

Max Range: 2.4954. Min Range: -2.4954

Max Act: 1.1296. Min Act: -0.0000

Data Index: 957697 (C4 (Web Text))

Max Activating Token Index: 537

Text #11

Max Range: 2.4954. Min Range: -2.4954

Max Act: 1.1139. Min Act: -0.0000

Data Index: 1108585 (C4 (Web Text))

Max Activating Token Index: 446

Text #12

Max Range: 2.4954. Min Range: -2.4954

Max Act: 1.0856. Min Act: -0.0000

Data Index: 1204805 (C4 (Web Text))

Max Activating Token Index: 609

Text #13

Max Range: 2.4954. Min Range: -2.4954

Max Act: 1.0630. Min Act: -0.0000

Data Index: 695623 (C4 (Web Text))

Max Activating Token Index: 56

Text #14

Max Range: 2.4954. Min Range: -2.4954

Max Act: 1.0068. Min Act: -0.0000

Data Index: 825734 (C4 (Web Text))

Max Activating Token Index: 46

Text #15

Max Range: 2.4954. Min Range: -2.4954

Max Act: 1.0210. Min Act: -0.0000

Data Index: 420524 (C4 (Web Text))

Max Activating Token Index: 1003

Text #16

Max Range: 2.4954. Min Range: -2.4954

Max Act: 1.0179. Min Act: -0.0000

Data Index: 406527 (C4 (Web Text))

Max Activating Token Index: 915

Text #17

Max Range: 2.4954. Min Range: -2.4954

Max Act: 0.9932. Min Act: -0.0000

Data Index: 1124175 (C4 (Web Text))

Max Activating Token Index: 615

Text #18

Max Range: 2.4954. Min Range: -2.4954

Max Act: 0.9855. Min Act: -0.0000

Data Index: 436994 (C4 (Web Text))

Max Activating Token Index: 984

Text #19

Max Range: 2.4954. Min Range: -2.4954

Max Act: 1.0502. Min Act: -0.0000

Data Index: 3752 (C4 (Web Text))

Max Activating Token Index: 37