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

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

Neuron 5973 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1902. Min Range: -2.1902

Max Act: 2.1902. Min Act: -0.0000

Data Index: 1243846 (C4 (Web Text))

Max Activating Token Index: 120

Text #1

Max Range: 2.1902. Min Range: -2.1902

Max Act: 2.1402. Min Act: -0.0000

Data Index: 761046 (C4 (Web Text))

Max Activating Token Index: 100

Text #2

Max Range: 2.1902. Min Range: -2.1902

Max Act: 2.0368. Min Act: -0.0000

Data Index: 210921 (C4 (Web Text))

Max Activating Token Index: 212

Text #3

Max Range: 2.1902. Min Range: -2.1902

Max Act: 2.0161. Min Act: -0.0000

Data Index: 737492 (C4 (Web Text))

Max Activating Token Index: 47

Text #4

Max Range: 2.1902. Min Range: -2.1902

Max Act: 1.9734. Min Act: -0.0000

Data Index: 1060387 (C4 (Web Text))

Max Activating Token Index: 74

Text #5

Max Range: 2.1902. Min Range: -2.1902

Max Act: 2.0806. Min Act: -0.0000

Data Index: 722108 (C4 (Web Text))

Max Activating Token Index: 404

Text #6

Max Range: 2.1902. Min Range: -2.1902

Max Act: 2.1714. Min Act: -0.0000

Data Index: 968970 (C4 (Web Text))

Max Activating Token Index: 297

Text #7

Max Range: 2.1902. Min Range: -2.1902

Max Act: 2.0213. Min Act: -0.0000

Data Index: 307327 (C4 (Web Text))

Max Activating Token Index: 529

Text #8

Max Range: 2.1902. Min Range: -2.1902

Max Act: 2.0127. Min Act: -0.0000

Data Index: 205846 (C4 (Web Text))

Max Activating Token Index: 869

Text #9

Max Range: 2.1902. Min Range: -2.1902

Max Act: 1.8846. Min Act: -0.0000

Data Index: 574546 (C4 (Web Text))

Max Activating Token Index: 974

Text #10

Max Range: 2.1902. Min Range: -2.1902

Max Act: 1.9841. Min Act: -0.0000

Data Index: 171161 (C4 (Web Text))

Max Activating Token Index: 89

Text #11

Max Range: 2.1902. Min Range: -2.1902

Max Act: 2.0090. Min Act: -0.0000

Data Index: 1341854 (C4 (Web Text))

Max Activating Token Index: 837

Text #12

Max Range: 2.1902. Min Range: -2.1902

Max Act: 1.8556. Min Act: -0.0000

Data Index: 714049 (C4 (Web Text))

Max Activating Token Index: 304

Text #13

Max Range: 2.1902. Min Range: -2.1902

Max Act: 1.9446. Min Act: -0.0000

Data Index: 47382 (C4 (Web Text))

Max Activating Token Index: 87

Text #14

Max Range: 2.1902. Min Range: -2.1902

Max Act: 1.9351. Min Act: -0.0000

Data Index: 193311 (C4 (Web Text))

Max Activating Token Index: 385

Text #15

Max Range: 2.1902. Min Range: -2.1902

Max Act: 1.9297. Min Act: -0.0000

Data Index: 911212 (C4 (Web Text))

Max Activating Token Index: 627

Text #16

Max Range: 2.1902. Min Range: -2.1902

Max Act: 1.7577. Min Act: -0.0000

Data Index: 1367295 (Python Code)

Max Activating Token Index: 387

Text #17

Max Range: 2.1902. Min Range: -2.1902

Max Act: 1.7981. Min Act: -0.0000

Data Index: 740944 (C4 (Web Text))

Max Activating Token Index: 683

Text #18

Max Range: 2.1902. Min Range: -2.1902

Max Act: 1.8848. Min Act: -0.0000

Data Index: 330445 (C4 (Web Text))

Max Activating Token Index: 637

Text #19

Max Range: 2.1902. Min Range: -2.1902

Max Act: 1.8649. Min Act: -0.0000

Data Index: 887983 (C4 (Web Text))

Max Activating Token Index: 16