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

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

Neuron 2350 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.5746. Min Range: -4.5746

Max Act: 4.5427. Min Act: -0.0000

Data Index: 1248454 (C4 (Web Text))

Max Activating Token Index: 27

Text #1

Max Range: 4.5746. Min Range: -4.5746

Max Act: 4.5746. Min Act: -0.0000

Data Index: 431357 (C4 (Web Text))

Max Activating Token Index: 111

Text #2

Max Range: 4.5746. Min Range: -4.5746

Max Act: 3.4503. Min Act: -0.0000

Data Index: 1180077 (C4 (Web Text))

Max Activating Token Index: 1005

Text #3

Max Range: 4.5746. Min Range: -4.5746

Max Act: 3.6221. Min Act: -0.0000

Data Index: 445829 (C4 (Web Text))

Max Activating Token Index: 684

Text #4

Max Range: 4.5746. Min Range: -4.5746

Max Act: 3.7120. Min Act: -0.0000

Data Index: 1087990 (C4 (Web Text))

Max Activating Token Index: 41

Text #5

Max Range: 4.5746. Min Range: -4.5746

Max Act: 3.4921. Min Act: -0.0000

Data Index: 270052 (C4 (Web Text))

Max Activating Token Index: 19

Text #6

Max Range: 4.5746. Min Range: -4.5746

Max Act: 3.7090. Min Act: -0.0000

Data Index: 487504 (C4 (Web Text))

Max Activating Token Index: 115

Text #7

Max Range: 4.5746. Min Range: -4.5746

Max Act: 3.3233. Min Act: -0.0000

Data Index: 369976 (C4 (Web Text))

Max Activating Token Index: 282

Text #8

Max Range: 4.5746. Min Range: -4.5746

Max Act: 2.8985. Min Act: -0.0000

Data Index: 306544 (C4 (Web Text))

Max Activating Token Index: 28

Text #9

Max Range: 4.5746. Min Range: -4.5746

Max Act: 2.9861. Min Act: -0.0000

Data Index: 3150 (C4 (Web Text))

Max Activating Token Index: 10

Text #10

Max Range: 4.5746. Min Range: -4.5746

Max Act: 2.8945. Min Act: -0.0000

Data Index: 706584 (C4 (Web Text))

Max Activating Token Index: 48

Text #11

Max Range: 4.5746. Min Range: -4.5746

Max Act: 2.5496. Min Act: -0.0000

Data Index: 265855 (C4 (Web Text))

Max Activating Token Index: 346

Text #12

Max Range: 4.5746. Min Range: -4.5746

Max Act: 2.7255. Min Act: -0.0000

Data Index: 431779 (C4 (Web Text))

Max Activating Token Index: 448

Text #13

Max Range: 4.5746. Min Range: -4.5746

Max Act: 2.6997. Min Act: -0.0000

Data Index: 577986 (C4 (Web Text))

Max Activating Token Index: 442

Text #14

Max Range: 4.5746. Min Range: -4.5746

Max Act: 2.7039. Min Act: -0.0000

Data Index: 640958 (C4 (Web Text))

Max Activating Token Index: 864

Text #15

Max Range: 4.5746. Min Range: -4.5746

Max Act: 2.5509. Min Act: -0.0000

Data Index: 274673 (C4 (Web Text))

Max Activating Token Index: 63

Text #16

Max Range: 4.5746. Min Range: -4.5746

Max Act: 2.8293. Min Act: -0.0000

Data Index: 770930 (C4 (Web Text))

Max Activating Token Index: 430

Text #17

Max Range: 4.5746. Min Range: -4.5746

Max Act: 2.6563. Min Act: -0.0000

Data Index: 534501 (C4 (Web Text))

Max Activating Token Index: 38

Text #18

Max Range: 4.5746. Min Range: -4.5746

Max Act: 2.6078. Min Act: -0.0000

Data Index: 225191 (C4 (Web Text))

Max Activating Token Index: 132

Text #19

Max Range: 4.5746. Min Range: -4.5746

Max Act: 2.4502. Min Act: -0.0000

Data Index: 1007757 (C4 (Web Text))

Max Activating Token Index: 257