Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3869 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.6092. Min Range: -3.6092

Max Act: 3.5666. Min Act: -0.0001

Data Index: 314738 (C4 (Web Text))

Max Activating Token Index: 909

Text #1

Max Range: 3.6092. Min Range: -3.6092

Max Act: 3.5517. Min Act: -0.0001

Data Index: 664684 (C4 (Web Text))

Max Activating Token Index: 891

Text #2

Max Range: 3.6092. Min Range: -3.6092

Max Act: 3.5542. Min Act: -0.0001

Data Index: 533527 (C4 (Web Text))

Max Activating Token Index: 457

Text #3

Max Range: 3.6092. Min Range: -3.6092

Max Act: 3.6092. Min Act: -0.0001

Data Index: 911452 (C4 (Web Text))

Max Activating Token Index: 492

Text #4

Max Range: 3.6092. Min Range: -3.6092

Max Act: 3.0336. Min Act: -0.0001

Data Index: 293727 (C4 (Web Text))

Max Activating Token Index: 993

Text #5

Max Range: 3.6092. Min Range: -3.6092

Max Act: 3.0179. Min Act: -0.0001

Data Index: 966005 (C4 (Web Text))

Max Activating Token Index: 687

Text #6

Max Range: 3.6092. Min Range: -3.6092

Max Act: 2.4227. Min Act: -0.0001

Data Index: 26913 (C4 (Web Text))

Max Activating Token Index: 167

Text #7

Max Range: 3.6092. Min Range: -3.6092

Max Act: 2.6538. Min Act: -0.0001

Data Index: 532819 (C4 (Web Text))

Max Activating Token Index: 620

Text #8

Max Range: 3.6092. Min Range: -3.6092

Max Act: 2.5776. Min Act: -0.0001

Data Index: 119777 (C4 (Web Text))

Max Activating Token Index: 93

Text #9

Max Range: 3.6092. Min Range: -3.6092

Max Act: 2.7734. Min Act: -0.0001

Data Index: 915917 (C4 (Web Text))

Max Activating Token Index: 343

Text #10

Max Range: 3.6092. Min Range: -3.6092

Max Act: 2.2122. Min Act: -0.0001

Data Index: 1013030 (C4 (Web Text))

Max Activating Token Index: 1009

Text #11

Max Range: 3.6092. Min Range: -3.6092

Max Act: 1.8813. Min Act: -0.0001

Data Index: 631982 (C4 (Web Text))

Max Activating Token Index: 725

Text #12

Max Range: 3.6092. Min Range: -3.6092

Max Act: 2.2262. Min Act: -0.0001

Data Index: 1357684 (C4 (Web Text))

Max Activating Token Index: 973

Text #13

Max Range: 3.6092. Min Range: -3.6092

Max Act: 2.3626. Min Act: -0.0001

Data Index: 845525 (C4 (Web Text))

Max Activating Token Index: 387

Text #14

Max Range: 3.6092. Min Range: -3.6092

Max Act: 2.4723. Min Act: -0.0001

Data Index: 771960 (C4 (Web Text))

Max Activating Token Index: 1002

Text #15

Max Range: 3.6092. Min Range: -3.6092

Max Act: 2.3477. Min Act: -0.0001

Data Index: 925639 (C4 (Web Text))

Max Activating Token Index: 841

Text #16

Max Range: 3.6092. Min Range: -3.6092

Max Act: 2.3066. Min Act: -0.0001

Data Index: 1226533 (C4 (Web Text))

Max Activating Token Index: 718

Text #17

Max Range: 3.6092. Min Range: -3.6092

Max Act: 2.3648. Min Act: -0.0001

Data Index: 90018 (C4 (Web Text))

Max Activating Token Index: 810

Text #18

Max Range: 3.6092. Min Range: -3.6092

Max Act: 2.3624. Min Act: -0.0001

Data Index: 563791 (C4 (Web Text))

Max Activating Token Index: 521

Text #19

Max Range: 3.6092. Min Range: -3.6092

Max Act: 2.0916. Min Act: -0.0001

Data Index: 391945 (C4 (Web Text))

Max Activating Token Index: 464