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

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

Neuron 3983 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9141. Min Range: -2.9141

Max Act: 2.9141. Min Act: -0.0000

Data Index: 356422 (C4 (Web Text))

Max Activating Token Index: 529

Text #1

Max Range: 2.9141. Min Range: -2.9141

Max Act: 2.5883. Min Act: -0.0000

Data Index: 457658 (C4 (Web Text))

Max Activating Token Index: 595

Text #2

Max Range: 2.9141. Min Range: -2.9141

Max Act: 2.1645. Min Act: -0.0000

Data Index: 777029 (C4 (Web Text))

Max Activating Token Index: 446

Text #3

Max Range: 2.9141. Min Range: -2.9141

Max Act: 2.3062. Min Act: -0.0000

Data Index: 1196267 (C4 (Web Text))

Max Activating Token Index: 845

Text #4

Max Range: 2.9141. Min Range: -2.9141

Max Act: 2.2626. Min Act: -0.0000

Data Index: 297224 (C4 (Web Text))

Max Activating Token Index: 89

Text #5

Max Range: 2.9141. Min Range: -2.9141

Max Act: 2.1045. Min Act: -0.0000

Data Index: 660771 (C4 (Web Text))

Max Activating Token Index: 696

Text #6

Max Range: 2.9141. Min Range: -2.9141

Max Act: 2.1764. Min Act: -0.0000

Data Index: 363797 (C4 (Web Text))

Max Activating Token Index: 825

Text #7

Max Range: 2.9141. Min Range: -2.9141

Max Act: 2.2988. Min Act: -0.0000

Data Index: 343142 (C4 (Web Text))

Max Activating Token Index: 978

Text #8

Max Range: 2.9141. Min Range: -2.9141

Max Act: 2.1470. Min Act: -0.0000

Data Index: 318323 (C4 (Web Text))

Max Activating Token Index: 156

Text #9

Max Range: 2.9141. Min Range: -2.9141

Max Act: 2.1293. Min Act: -0.0000

Data Index: 470925 (C4 (Web Text))

Max Activating Token Index: 986

Text #10

Max Range: 2.9141. Min Range: -2.9141

Max Act: 2.2378. Min Act: -0.0000

Data Index: 318062 (C4 (Web Text))

Max Activating Token Index: 849

Text #11

Max Range: 2.9141. Min Range: -2.9141

Max Act: 2.0105. Min Act: -0.0000

Data Index: 411062 (C4 (Web Text))

Max Activating Token Index: 688

Text #12

Max Range: 2.9141. Min Range: -2.9141

Max Act: 2.1491. Min Act: -0.0000

Data Index: 108491 (C4 (Web Text))

Max Activating Token Index: 649

Text #13

Max Range: 2.9141. Min Range: -2.9141

Max Act: 2.0259. Min Act: -0.0000

Data Index: 1270942 (C4 (Web Text))

Max Activating Token Index: 385

Text #14

Max Range: 2.9141. Min Range: -2.9141

Max Act: 2.0298. Min Act: -0.0000

Data Index: 1067625 (C4 (Web Text))

Max Activating Token Index: 24

Text #15

Max Range: 2.9141. Min Range: -2.9141

Max Act: 1.9008. Min Act: -0.0000

Data Index: 1307331 (C4 (Web Text))

Max Activating Token Index: 893

Text #16

Max Range: 2.9141. Min Range: -2.9141

Max Act: 2.0949. Min Act: -0.0000

Data Index: 206355 (C4 (Web Text))

Max Activating Token Index: 539

Text #17

Max Range: 2.9141. Min Range: -2.9141

Max Act: 2.0978. Min Act: -0.0000

Data Index: 160238 (C4 (Web Text))

Max Activating Token Index: 474

Text #18

Max Range: 2.9141. Min Range: -2.9141

Max Act: 1.8703. Min Act: -0.0000

Data Index: 527856 (C4 (Web Text))

Max Activating Token Index: 686

Text #19

Max Range: 2.9141. Min Range: -2.9141

Max Act: 1.7314. Min Act: -0.0000

Data Index: 775975 (C4 (Web Text))

Max Activating Token Index: 966