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

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

Neuron 1031 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: 0.3908. Min Range: -0.3908

Max Act: 0.3782. Min Act: -0.0000

Data Index: 839199 (C4 (Web Text))

Max Activating Token Index: 235

Text #1

Max Range: 0.3908. Min Range: -0.3908

Max Act: 0.3908. Min Act: -0.0000

Data Index: 1138456 (C4 (Web Text))

Max Activating Token Index: 884

Text #2

Max Range: 0.3908. Min Range: -0.3908

Max Act: 0.3587. Min Act: -0.0000

Data Index: 1300554 (C4 (Web Text))

Max Activating Token Index: 59

Text #3

Max Range: 0.3908. Min Range: -0.3908

Max Act: 0.3768. Min Act: -0.0000

Data Index: 489741 (C4 (Web Text))

Max Activating Token Index: 19

Text #4

Max Range: 0.3908. Min Range: -0.3908

Max Act: 0.3555. Min Act: -0.0000

Data Index: 418703 (C4 (Web Text))

Max Activating Token Index: 791

Text #5

Max Range: 0.3908. Min Range: -0.3908

Max Act: 0.3588. Min Act: -0.0000

Data Index: 1173374 (C4 (Web Text))

Max Activating Token Index: 461

Text #6

Max Range: 0.3908. Min Range: -0.3908

Max Act: 0.3681. Min Act: -0.0000

Data Index: 1031762 (C4 (Web Text))

Max Activating Token Index: 701

Text #7

Max Range: 0.3908. Min Range: -0.3908

Max Act: 0.3647. Min Act: -0.0000

Data Index: 131342 (C4 (Web Text))

Max Activating Token Index: 313

Text #8

Max Range: 0.3908. Min Range: -0.3908

Max Act: 0.3274. Min Act: -0.0000

Data Index: 52645 (C4 (Web Text))

Max Activating Token Index: 755

Text #9

Max Range: 0.3908. Min Range: -0.3908

Max Act: 0.3411. Min Act: -0.0000

Data Index: 887686 (C4 (Web Text))

Max Activating Token Index: 255

Text #10

Max Range: 0.3908. Min Range: -0.3908

Max Act: 0.3463. Min Act: -0.0000

Data Index: 1215696 (C4 (Web Text))

Max Activating Token Index: 128

Text #11

Max Range: 0.3908. Min Range: -0.3908

Max Act: 0.3268. Min Act: -0.0000

Data Index: 521111 (C4 (Web Text))

Max Activating Token Index: 174

Text #12

Max Range: 0.3908. Min Range: -0.3908

Max Act: 0.3408. Min Act: -0.0000

Data Index: 1054517 (C4 (Web Text))

Max Activating Token Index: 17

Text #13

Max Range: 0.3908. Min Range: -0.3908

Max Act: 0.3070. Min Act: -0.0000

Data Index: 1307623 (C4 (Web Text))

Max Activating Token Index: 311

Text #14

Max Range: 0.3908. Min Range: -0.3908

Max Act: 0.3485. Min Act: -0.0000

Data Index: 959370 (C4 (Web Text))

Max Activating Token Index: 531

Text #15

Max Range: 0.3908. Min Range: -0.3908

Max Act: 0.3132. Min Act: -0.0000

Data Index: 852369 (C4 (Web Text))

Max Activating Token Index: 316

Text #16

Max Range: 0.3908. Min Range: -0.3908

Max Act: 0.3038. Min Act: -0.0000

Data Index: 1132492 (C4 (Web Text))

Max Activating Token Index: 885

Text #17

Max Range: 0.3908. Min Range: -0.3908

Max Act: 0.3080. Min Act: -0.0000

Data Index: 1332230 (C4 (Web Text))

Max Activating Token Index: 937

Text #18

Max Range: 0.3908. Min Range: -0.3908

Max Act: 0.2705. Min Act: -0.0000

Data Index: 523025 (C4 (Web Text))

Max Activating Token Index: 776

Text #19

Max Range: 0.3908. Min Range: -0.3908

Max Act: 0.3067. Min Act: -0.0000

Data Index: 170625 (C4 (Web Text))

Max Activating Token Index: 973