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

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

Neuron 4778 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.5107. Min Range: -4.5107

Max Act: 4.5107. Min Act: -0.0000

Data Index: 491548 (C4 (Web Text))

Max Activating Token Index: 999

Text #1

Max Range: 4.5107. Min Range: -4.5107

Max Act: 3.2340. Min Act: -0.0000

Data Index: 1283540 (C4 (Web Text))

Max Activating Token Index: 728

Text #2

Max Range: 4.5107. Min Range: -4.5107

Max Act: 2.7522. Min Act: -0.0000

Data Index: 295138 (C4 (Web Text))

Max Activating Token Index: 894

Text #3

Max Range: 4.5107. Min Range: -4.5107

Max Act: 2.4370. Min Act: -0.0000

Data Index: 781653 (C4 (Web Text))

Max Activating Token Index: 697

Text #4

Max Range: 4.5107. Min Range: -4.5107

Max Act: 2.4430. Min Act: -0.0000

Data Index: 1333685 (C4 (Web Text))

Max Activating Token Index: 107

Text #5

Max Range: 4.5107. Min Range: -4.5107

Max Act: 2.2756. Min Act: -0.0000

Data Index: 1318852 (C4 (Web Text))

Max Activating Token Index: 586

Text #6

Max Range: 4.5107. Min Range: -4.5107

Max Act: 2.3272. Min Act: -0.0000

Data Index: 984933 (C4 (Web Text))

Max Activating Token Index: 820

Text #7

Max Range: 4.5107. Min Range: -4.5107

Max Act: 2.4461. Min Act: -0.0000

Data Index: 846475 (C4 (Web Text))

Max Activating Token Index: 786

Text #8

Max Range: 4.5107. Min Range: -4.5107

Max Act: 2.1971. Min Act: -0.0000

Data Index: 805790 (C4 (Web Text))

Max Activating Token Index: 534

Text #9

Max Range: 4.5107. Min Range: -4.5107

Max Act: 2.1773. Min Act: -0.0000

Data Index: 102452 (C4 (Web Text))

Max Activating Token Index: 315

Text #10

Max Range: 4.5107. Min Range: -4.5107

Max Act: 2.1596. Min Act: -0.0000

Data Index: 608923 (C4 (Web Text))

Max Activating Token Index: 647

Text #11

Max Range: 4.5107. Min Range: -4.5107

Max Act: 2.1183. Min Act: -0.0000

Data Index: 795944 (C4 (Web Text))

Max Activating Token Index: 397

Text #12

Max Range: 4.5107. Min Range: -4.5107

Max Act: 1.9067. Min Act: -0.0000

Data Index: 991687 (C4 (Web Text))

Max Activating Token Index: 773

Text #13

Max Range: 4.5107. Min Range: -4.5107

Max Act: 2.1797. Min Act: -0.0000

Data Index: 1115409 (C4 (Web Text))

Max Activating Token Index: 672

Text #14

Max Range: 4.5107. Min Range: -4.5107

Max Act: 1.9064. Min Act: -0.0000

Data Index: 580201 (C4 (Web Text))

Max Activating Token Index: 1006

Text #15

Max Range: 4.5107. Min Range: -4.5107

Max Act: 1.9652. Min Act: -0.0000

Data Index: 170092 (C4 (Web Text))

Max Activating Token Index: 789

Text #16

Max Range: 4.5107. Min Range: -4.5107

Max Act: 1.9480. Min Act: -0.0000

Data Index: 930180 (C4 (Web Text))

Max Activating Token Index: 167

Text #17

Max Range: 4.5107. Min Range: -4.5107

Max Act: 1.9989. Min Act: -0.0000

Data Index: 1345041 (C4 (Web Text))

Max Activating Token Index: 496

Text #18

Max Range: 4.5107. Min Range: -4.5107

Max Act: 1.9421. Min Act: -0.0000

Data Index: 1308550 (C4 (Web Text))

Max Activating Token Index: 538

Text #19

Max Range: 4.5107. Min Range: -4.5107

Max Act: 1.7047. Min Act: -0.0000

Data Index: 36185 (C4 (Web Text))

Max Activating Token Index: 240