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

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

Neuron 398 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3935. Min Range: -5.3935

Max Act: 5.3935. Min Act: -0.0000

Data Index: 536312 (C4 (Web Text))

Max Activating Token Index: 134

Text #1

Max Range: 5.3935. Min Range: -5.3935

Max Act: 4.8047. Min Act: -0.0000

Data Index: 529190 (C4 (Web Text))

Max Activating Token Index: 917

Text #2

Max Range: 5.3935. Min Range: -5.3935

Max Act: 4.8668. Min Act: -0.0000

Data Index: 1110853 (C4 (Web Text))

Max Activating Token Index: 32

Text #3

Max Range: 5.3935. Min Range: -5.3935

Max Act: 4.9894. Min Act: -0.0000

Data Index: 318379 (C4 (Web Text))

Max Activating Token Index: 272

Text #4

Max Range: 5.3935. Min Range: -5.3935

Max Act: 4.5898. Min Act: -0.0000

Data Index: 62470 (C4 (Web Text))

Max Activating Token Index: 731

Text #5

Max Range: 5.3935. Min Range: -5.3935

Max Act: 4.7426. Min Act: -0.0000

Data Index: 1204046 (C4 (Web Text))

Max Activating Token Index: 145

Text #6

Max Range: 5.3935. Min Range: -5.3935

Max Act: 4.8831. Min Act: -0.0000

Data Index: 282843 (C4 (Web Text))

Max Activating Token Index: 825

Text #7

Max Range: 5.3935. Min Range: -5.3935

Max Act: 4.5847. Min Act: -0.0000

Data Index: 1117144 (C4 (Web Text))

Max Activating Token Index: 919

Text #8

Max Range: 5.3935. Min Range: -5.3935

Max Act: 4.5703. Min Act: -0.0000

Data Index: 842302 (C4 (Web Text))

Max Activating Token Index: 872

Text #9

Max Range: 5.3935. Min Range: -5.3935

Max Act: 4.5624. Min Act: -0.0000

Data Index: 373120 (C4 (Web Text))

Max Activating Token Index: 449

Text #10

Max Range: 5.3935. Min Range: -5.3935

Max Act: 4.5573. Min Act: -0.0000

Data Index: 1045120 (C4 (Web Text))

Max Activating Token Index: 211

Text #11

Max Range: 5.3935. Min Range: -5.3935

Max Act: 4.5275. Min Act: -0.0000

Data Index: 543995 (C4 (Web Text))

Max Activating Token Index: 666

Text #12

Max Range: 5.3935. Min Range: -5.3935

Max Act: 4.5438. Min Act: -0.0000

Data Index: 1038780 (C4 (Web Text))

Max Activating Token Index: 692

Text #13

Max Range: 5.3935. Min Range: -5.3935

Max Act: 4.4898. Min Act: -0.0000

Data Index: 1244445 (C4 (Web Text))

Max Activating Token Index: 30

Text #14

Max Range: 5.3935. Min Range: -5.3935

Max Act: 4.4181. Min Act: -0.0000

Data Index: 1113853 (C4 (Web Text))

Max Activating Token Index: 708

Text #15

Max Range: 5.3935. Min Range: -5.3935

Max Act: 4.3848. Min Act: -0.0000

Data Index: 1030965 (C4 (Web Text))

Max Activating Token Index: 895

Text #16

Max Range: 5.3935. Min Range: -5.3935

Max Act: 4.2127. Min Act: -0.0000

Data Index: 675842 (C4 (Web Text))

Max Activating Token Index: 740

Text #17

Max Range: 5.3935. Min Range: -5.3935

Max Act: 4.2332. Min Act: -0.0000

Data Index: 806218 (C4 (Web Text))

Max Activating Token Index: 732

Text #18

Max Range: 5.3935. Min Range: -5.3935

Max Act: 4.3378. Min Act: -0.0000

Data Index: 736558 (C4 (Web Text))

Max Activating Token Index: 644

Text #19

Max Range: 5.3935. Min Range: -5.3935

Max Act: 4.3479. Min Act: -0.0000

Data Index: 486401 (C4 (Web Text))

Max Activating Token Index: 19