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

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

Neuron 4917 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4659. Min Range: -1.4659

Max Act: 1.4659. Min Act: -0.0000

Data Index: 668905 (C4 (Web Text))

Max Activating Token Index: 221

Text #1

Max Range: 1.4659. Min Range: -1.4659

Max Act: 1.2081. Min Act: -0.0000

Data Index: 688586 (C4 (Web Text))

Max Activating Token Index: 54

Text #2

Max Range: 1.4659. Min Range: -1.4659

Max Act: 1.2368. Min Act: -0.0000

Data Index: 780296 (C4 (Web Text))

Max Activating Token Index: 844

Text #3

Max Range: 1.4659. Min Range: -1.4659

Max Act: 1.0873. Min Act: -0.0000

Data Index: 1135252 (C4 (Web Text))

Max Activating Token Index: 469

Text #4

Max Range: 1.4659. Min Range: -1.4659

Max Act: 1.1095. Min Act: -0.0000

Data Index: 736053 (C4 (Web Text))

Max Activating Token Index: 272

Text #5

Max Range: 1.4659. Min Range: -1.4659

Max Act: 1.0984. Min Act: -0.0000

Data Index: 1353342 (C4 (Web Text))

Max Activating Token Index: 72

Text #6

Max Range: 1.4659. Min Range: -1.4659

Max Act: 1.0439. Min Act: -0.0000

Data Index: 816616 (C4 (Web Text))

Max Activating Token Index: 461

Text #7

Max Range: 1.4659. Min Range: -1.4659

Max Act: 1.0344. Min Act: -0.0000

Data Index: 765527 (C4 (Web Text))

Max Activating Token Index: 52

Text #8

Max Range: 1.4659. Min Range: -1.4659

Max Act: 0.9907. Min Act: -0.0000

Data Index: 61104 (C4 (Web Text))

Max Activating Token Index: 301

Text #9

Max Range: 1.4659. Min Range: -1.4659

Max Act: 0.8975. Min Act: -0.0000

Data Index: 210544 (C4 (Web Text))

Max Activating Token Index: 706

Text #10

Max Range: 1.4659. Min Range: -1.4659

Max Act: 0.9874. Min Act: -0.0000

Data Index: 379518 (C4 (Web Text))

Max Activating Token Index: 787

Text #11

Max Range: 1.4659. Min Range: -1.4659

Max Act: 1.0018. Min Act: -0.0000

Data Index: 326978 (C4 (Web Text))

Max Activating Token Index: 184

Text #12

Max Range: 1.4659. Min Range: -1.4659

Max Act: 1.0136. Min Act: -0.0000

Data Index: 947953 (C4 (Web Text))

Max Activating Token Index: 29

Text #13

Max Range: 1.4659. Min Range: -1.4659

Max Act: 1.0032. Min Act: -0.0000

Data Index: 180882 (C4 (Web Text))

Max Activating Token Index: 179

Text #14

Max Range: 1.4659. Min Range: -1.4659

Max Act: 0.9300. Min Act: -0.0000

Data Index: 522374 (C4 (Web Text))

Max Activating Token Index: 930

Text #15

Max Range: 1.4659. Min Range: -1.4659

Max Act: 1.0135. Min Act: -0.0000

Data Index: 936646 (C4 (Web Text))

Max Activating Token Index: 747

Text #16

Max Range: 1.4659. Min Range: -1.4659

Max Act: 0.9297. Min Act: -0.0000

Data Index: 1341328 (C4 (Web Text))

Max Activating Token Index: 182

Text #17

Max Range: 1.4659. Min Range: -1.4659

Max Act: 0.9521. Min Act: -0.0000

Data Index: 147042 (C4 (Web Text))

Max Activating Token Index: 702

Text #18

Max Range: 1.4659. Min Range: -1.4659

Max Act: 0.9475. Min Act: -0.0000

Data Index: 1158064 (C4 (Web Text))

Max Activating Token Index: 420

Text #19

Max Range: 1.4659. Min Range: -1.4659

Max Act: 0.8861. Min Act: -0.0000

Data Index: 451380 (C4 (Web Text))

Max Activating Token Index: 695