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

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

Neuron 122 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: 2.2412. Min Range: -2.2412

Max Act: 2.2412. Min Act: -0.0000

Data Index: 301123 (C4 (Web Text))

Max Activating Token Index: 879

Text #1

Max Range: 2.2412. Min Range: -2.2412

Max Act: 2.2296. Min Act: 0.0000

Data Index: 723984 (C4 (Web Text))

Max Activating Token Index: 837

Text #2

Max Range: 2.2412. Min Range: -2.2412

Max Act: 2.0996. Min Act: -0.0000

Data Index: 521426 (C4 (Web Text))

Max Activating Token Index: 775

Text #3

Max Range: 2.2412. Min Range: -2.2412

Max Act: 2.0780. Min Act: 0.0001

Data Index: 292417 (C4 (Web Text))

Max Activating Token Index: 139

Text #4

Max Range: 2.2412. Min Range: -2.2412

Max Act: 2.1663. Min Act: 0.0000

Data Index: 913492 (C4 (Web Text))

Max Activating Token Index: 972

Text #5

Max Range: 2.2412. Min Range: -2.2412

Max Act: 2.1674. Min Act: -0.0000

Data Index: 1145140 (C4 (Web Text))

Max Activating Token Index: 275

Text #6

Max Range: 2.2412. Min Range: -2.2412

Max Act: 2.1558. Min Act: -0.0000

Data Index: 372073 (C4 (Web Text))

Max Activating Token Index: 855

Text #7

Max Range: 2.2412. Min Range: -2.2412

Max Act: 2.0007. Min Act: -0.0000

Data Index: 125829 (C4 (Web Text))

Max Activating Token Index: 1013

Text #8

Max Range: 2.2412. Min Range: -2.2412

Max Act: 2.1046. Min Act: -0.0000

Data Index: 244577 (C4 (Web Text))

Max Activating Token Index: 1003

Text #9

Max Range: 2.2412. Min Range: -2.2412

Max Act: 2.0699. Min Act: -0.0000

Data Index: 74700 (C4 (Web Text))

Max Activating Token Index: 196

Text #10

Max Range: 2.2412. Min Range: -2.2412

Max Act: 1.7603. Min Act: -0.0000

Data Index: 68387 (C4 (Web Text))

Max Activating Token Index: 735

Text #11

Max Range: 2.2412. Min Range: -2.2412

Max Act: 1.9084. Min Act: 0.0000

Data Index: 550380 (C4 (Web Text))

Max Activating Token Index: 121

Text #12

Max Range: 2.2412. Min Range: -2.2412

Max Act: 1.9722. Min Act: -0.0000

Data Index: 659790 (C4 (Web Text))

Max Activating Token Index: 448

Text #13

Max Range: 2.2412. Min Range: -2.2412

Max Act: 1.9626. Min Act: -0.0000

Data Index: 1092125 (C4 (Web Text))

Max Activating Token Index: 820

Text #14

Max Range: 2.2412. Min Range: -2.2412

Max Act: 2.0505. Min Act: 0.0000

Data Index: 1064363 (C4 (Web Text))

Max Activating Token Index: 973

Text #15

Max Range: 2.2412. Min Range: -2.2412

Max Act: 1.9483. Min Act: 0.0001

Data Index: 610131 (C4 (Web Text))

Max Activating Token Index: 608

Text #16

Max Range: 2.2412. Min Range: -2.2412

Max Act: 1.9375. Min Act: 0.0000

Data Index: 585300 (C4 (Web Text))

Max Activating Token Index: 290

Text #17

Max Range: 2.2412. Min Range: -2.2412

Max Act: 1.7516. Min Act: 0.0000

Data Index: 393963 (C4 (Web Text))

Max Activating Token Index: 127

Text #18

Max Range: 2.2412. Min Range: -2.2412

Max Act: 1.9358. Min Act: 0.0001

Data Index: 53904 (C4 (Web Text))

Max Activating Token Index: 900

Text #19

Max Range: 2.2412. Min Range: -2.2412

Max Act: 1.9040. Min Act: -0.0000

Data Index: 350683 (C4 (Web Text))

Max Activating Token Index: 756