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

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

Neuron 228 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: 2.2712. Min Range: -2.2712

Max Act: 2.2712. Min Act: -0.0000

Data Index: 304427 (C4 (Web Text))

Max Activating Token Index: 962

Text #1

Max Range: 2.2712. Min Range: -2.2712

Max Act: 2.0973. Min Act: 0.0001

Data Index: 1247419 (C4 (Web Text))

Max Activating Token Index: 921

Text #2

Max Range: 2.2712. Min Range: -2.2712

Max Act: 2.0705. Min Act: 0.0000

Data Index: 1024968 (C4 (Web Text))

Max Activating Token Index: 427

Text #3

Max Range: 2.2712. Min Range: -2.2712

Max Act: 1.8007. Min Act: -0.0000

Data Index: 792678 (C4 (Web Text))

Max Activating Token Index: 675

Text #4

Max Range: 2.2712. Min Range: -2.2712

Max Act: 1.7252. Min Act: 0.0001

Data Index: 708903 (C4 (Web Text))

Max Activating Token Index: 904

Text #5

Max Range: 2.2712. Min Range: -2.2712

Max Act: 1.6584. Min Act: 0.0000

Data Index: 987435 (C4 (Web Text))

Max Activating Token Index: 546

Text #6

Max Range: 2.2712. Min Range: -2.2712

Max Act: 1.6577. Min Act: -0.0000

Data Index: 571677 (C4 (Web Text))

Max Activating Token Index: 901

Text #7

Max Range: 2.2712. Min Range: -2.2712

Max Act: 1.6181. Min Act: -0.0000

Data Index: 995948 (C4 (Web Text))

Max Activating Token Index: 865

Text #8

Max Range: 2.2712. Min Range: -2.2712

Max Act: 1.5971. Min Act: -0.0000

Data Index: 243665 (C4 (Web Text))

Max Activating Token Index: 87

Text #9

Max Range: 2.2712. Min Range: -2.2712

Max Act: 1.5703. Min Act: -0.0000

Data Index: 1485067 (Python Code)

Max Activating Token Index: 853

Text #10

Max Range: 2.2712. Min Range: -2.2712

Max Act: 1.5645. Min Act: -0.0000

Data Index: 325646 (C4 (Web Text))

Max Activating Token Index: 141

Text #11

Max Range: 2.2712. Min Range: -2.2712

Max Act: 1.5625. Min Act: -0.0000

Data Index: 1246909 (C4 (Web Text))

Max Activating Token Index: 784

Text #12

Max Range: 2.2712. Min Range: -2.2712

Max Act: 1.5315. Min Act: 0.0001

Data Index: 264263 (C4 (Web Text))

Max Activating Token Index: 981

Text #13

Max Range: 2.2712. Min Range: -2.2712

Max Act: 1.5219. Min Act: -0.0000

Data Index: 938341 (C4 (Web Text))

Max Activating Token Index: 716

Text #14

Max Range: 2.2712. Min Range: -2.2712

Max Act: 1.5145. Min Act: 0.0000

Data Index: 1023130 (C4 (Web Text))

Max Activating Token Index: 692

Text #15

Max Range: 2.2712. Min Range: -2.2712

Max Act: 1.4247. Min Act: 0.0000

Data Index: 163197 (C4 (Web Text))

Max Activating Token Index: 389

Text #16

Max Range: 2.2712. Min Range: -2.2712

Max Act: 1.5724. Min Act: -0.0000

Data Index: 22152 (C4 (Web Text))

Max Activating Token Index: 1014

Text #17

Max Range: 2.2712. Min Range: -2.2712

Max Act: 1.5006. Min Act: -0.0000

Data Index: 273673 (C4 (Web Text))

Max Activating Token Index: 183

Text #18

Max Range: 2.2712. Min Range: -2.2712

Max Act: 1.4109. Min Act: 0.0000

Data Index: 1344138 (C4 (Web Text))

Max Activating Token Index: 379

Text #19

Max Range: 2.2712. Min Range: -2.2712

Max Act: 1.4797. Min Act: -0.0000

Data Index: 102564 (C4 (Web Text))

Max Activating Token Index: 509