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

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

Neuron 3520 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: 1.7732. Min Range: -1.7732

Max Act: 1.7732. Min Act: -0.0000

Data Index: 652926 (C4 (Web Text))

Max Activating Token Index: 622

Text #1

Max Range: 1.7732. Min Range: -1.7732

Max Act: 1.7605. Min Act: -0.0000

Data Index: 394896 (C4 (Web Text))

Max Activating Token Index: 920

Text #2

Max Range: 1.7732. Min Range: -1.7732

Max Act: 1.6183. Min Act: 0.0000

Data Index: 1000374 (C4 (Web Text))

Max Activating Token Index: 865

Text #3

Max Range: 1.7732. Min Range: -1.7732

Max Act: 1.6157. Min Act: -0.0000

Data Index: 374088 (C4 (Web Text))

Max Activating Token Index: 869

Text #4

Max Range: 1.7732. Min Range: -1.7732

Max Act: 1.3214. Min Act: -0.0000

Data Index: 51767 (C4 (Web Text))

Max Activating Token Index: 319

Text #5

Max Range: 1.7732. Min Range: -1.7732

Max Act: 1.2982. Min Act: -0.0000

Data Index: 1185456 (C4 (Web Text))

Max Activating Token Index: 326

Text #6

Max Range: 1.7732. Min Range: -1.7732

Max Act: 1.1269. Min Act: 0.0000

Data Index: 524381 (C4 (Web Text))

Max Activating Token Index: 438

Text #7

Max Range: 1.7732. Min Range: -1.7732

Max Act: 1.1411. Min Act: 0.0000

Data Index: 850426 (C4 (Web Text))

Max Activating Token Index: 696

Text #8

Max Range: 1.7732. Min Range: -1.7732

Max Act: 1.0989. Min Act: -0.0000

Data Index: 403799 (C4 (Web Text))

Max Activating Token Index: 995

Text #9

Max Range: 1.7732. Min Range: -1.7732

Max Act: 1.1114. Min Act: -0.0000

Data Index: 75935 (C4 (Web Text))

Max Activating Token Index: 223

Text #10

Max Range: 1.7732. Min Range: -1.7732

Max Act: 1.1466. Min Act: -0.0000

Data Index: 660063 (C4 (Web Text))

Max Activating Token Index: 565

Text #11

Max Range: 1.7732. Min Range: -1.7732

Max Act: 1.0549. Min Act: -0.0000

Data Index: 981810 (C4 (Web Text))

Max Activating Token Index: 146

Text #12

Max Range: 1.7732. Min Range: -1.7732

Max Act: 1.0679. Min Act: -0.0000

Data Index: 283104 (C4 (Web Text))

Max Activating Token Index: 416

Text #13

Max Range: 1.7732. Min Range: -1.7732

Max Act: 1.0260. Min Act: -0.0000

Data Index: 102949 (C4 (Web Text))

Max Activating Token Index: 468

Text #14

Max Range: 1.7732. Min Range: -1.7732

Max Act: 1.0575. Min Act: -0.0000

Data Index: 1019195 (C4 (Web Text))

Max Activating Token Index: 594

Text #15

Max Range: 1.7732. Min Range: -1.7732

Max Act: 1.0767. Min Act: -0.0000

Data Index: 766370 (C4 (Web Text))

Max Activating Token Index: 991

Text #16

Max Range: 1.7732. Min Range: -1.7732

Max Act: 0.9873. Min Act: -0.0000

Data Index: 991149 (C4 (Web Text))

Max Activating Token Index: 278

Text #17

Max Range: 1.7732. Min Range: -1.7732

Max Act: 1.0455. Min Act: -0.0000

Data Index: 483670 (C4 (Web Text))

Max Activating Token Index: 788

Text #18

Max Range: 1.7732. Min Range: -1.7732

Max Act: 1.0316. Min Act: -0.0000

Data Index: 906900 (C4 (Web Text))

Max Activating Token Index: 1005

Text #19

Max Range: 1.7732. Min Range: -1.7732

Max Act: 0.9831. Min Act: -0.0000

Data Index: 1088601 (C4 (Web Text))

Max Activating Token Index: 991