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

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

Neuron 3733 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3307. Min Range: -1.3307

Max Act: 1.3307. Min Act: -0.0000

Data Index: 18750 (C4 (Web Text))

Max Activating Token Index: 413

Text #1

Max Range: 1.3307. Min Range: -1.3307

Max Act: 1.1667. Min Act: 0.0000

Data Index: 962158 (C4 (Web Text))

Max Activating Token Index: 310

Text #2

Max Range: 1.3307. Min Range: -1.3307

Max Act: 1.1551. Min Act: -0.0000

Data Index: 617185 (C4 (Web Text))

Max Activating Token Index: 775

Text #3

Max Range: 1.3307. Min Range: -1.3307

Max Act: 1.0767. Min Act: -0.0000

Data Index: 56388 (C4 (Web Text))

Max Activating Token Index: 155

Text #4

Max Range: 1.3307. Min Range: -1.3307

Max Act: 1.0122. Min Act: -0.0000

Data Index: 931295 (C4 (Web Text))

Max Activating Token Index: 61

Text #5

Max Range: 1.3307. Min Range: -1.3307

Max Act: 1.0068. Min Act: 0.0000

Data Index: 1276779 (C4 (Web Text))

Max Activating Token Index: 697

Text #6

Max Range: 1.3307. Min Range: -1.3307

Max Act: 0.9967. Min Act: -0.0000

Data Index: 1161065 (C4 (Web Text))

Max Activating Token Index: 812

Text #7

Max Range: 1.3307. Min Range: -1.3307

Max Act: 0.9205. Min Act: -0.0000

Data Index: 1070717 (C4 (Web Text))

Max Activating Token Index: 765

Text #8

Max Range: 1.3307. Min Range: -1.3307

Max Act: 0.9636. Min Act: -0.0000

Data Index: 383400 (C4 (Web Text))

Max Activating Token Index: 622

Text #9

Max Range: 1.3307. Min Range: -1.3307

Max Act: 0.9064. Min Act: -0.0000

Data Index: 702883 (C4 (Web Text))

Max Activating Token Index: 994

Text #10

Max Range: 1.3307. Min Range: -1.3307

Max Act: 0.9190. Min Act: -0.0000

Data Index: 150896 (C4 (Web Text))

Max Activating Token Index: 849

Text #11

Max Range: 1.3307. Min Range: -1.3307

Max Act: 0.9535. Min Act: 0.0000

Data Index: 459016 (C4 (Web Text))

Max Activating Token Index: 626

Text #12

Max Range: 1.3307. Min Range: -1.3307

Max Act: 0.8574. Min Act: -0.0000

Data Index: 1021466 (C4 (Web Text))

Max Activating Token Index: 226

Text #13

Max Range: 1.3307. Min Range: -1.3307

Max Act: 0.9577. Min Act: -0.0000

Data Index: 647168 (C4 (Web Text))

Max Activating Token Index: 53

Text #14

Max Range: 1.3307. Min Range: -1.3307

Max Act: 0.9234. Min Act: -0.0000

Data Index: 128785 (C4 (Web Text))

Max Activating Token Index: 158

Text #15

Max Range: 1.3307. Min Range: -1.3307

Max Act: 0.9213. Min Act: 0.0000

Data Index: 113428 (C4 (Web Text))

Max Activating Token Index: 305

Text #16

Max Range: 1.3307. Min Range: -1.3307

Max Act: 0.8783. Min Act: -0.0000

Data Index: 2559 (C4 (Web Text))

Max Activating Token Index: 425

Text #17

Max Range: 1.3307. Min Range: -1.3307

Max Act: 0.8825. Min Act: -0.0000

Data Index: 701677 (C4 (Web Text))

Max Activating Token Index: 729

Text #18

Max Range: 1.3307. Min Range: -1.3307

Max Act: 0.9104. Min Act: -0.0000

Data Index: 1069486 (C4 (Web Text))

Max Activating Token Index: 807

Text #19

Max Range: 1.3307. Min Range: -1.3307

Max Act: 0.8889. Min Act: -0.0000

Data Index: 987063 (C4 (Web Text))

Max Activating Token Index: 1013