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

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

Neuron 2716 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7988. Min Range: -3.7988

Max Act: 3.7004. Min Act: -0.0000

Data Index: 541248 (C4 (Web Text))

Max Activating Token Index: 89

Text #1

Max Range: 3.7988. Min Range: -3.7988

Max Act: 3.7988. Min Act: -0.0000

Data Index: 468590 (C4 (Web Text))

Max Activating Token Index: 6

Text #2

Max Range: 3.7988. Min Range: -3.7988

Max Act: 3.4704. Min Act: -0.0000

Data Index: 497739 (C4 (Web Text))

Max Activating Token Index: 695

Text #3

Max Range: 3.7988. Min Range: -3.7988

Max Act: 3.1595. Min Act: -0.0000

Data Index: 519646 (C4 (Web Text))

Max Activating Token Index: 323

Text #4

Max Range: 3.7988. Min Range: -3.7988

Max Act: 3.4196. Min Act: -0.0000

Data Index: 1183282 (C4 (Web Text))

Max Activating Token Index: 237

Text #5

Max Range: 3.7988. Min Range: -3.7988

Max Act: 3.1810. Min Act: -0.0000

Data Index: 352142 (C4 (Web Text))

Max Activating Token Index: 58

Text #6

Max Range: 3.7988. Min Range: -3.7988

Max Act: 3.1901. Min Act: -0.0000

Data Index: 871731 (C4 (Web Text))

Max Activating Token Index: 481

Text #7

Max Range: 3.7988. Min Range: -3.7988

Max Act: 3.3083. Min Act: -0.0000

Data Index: 1224654 (C4 (Web Text))

Max Activating Token Index: 994

Text #8

Max Range: 3.7988. Min Range: -3.7988

Max Act: 3.1594. Min Act: -0.0000

Data Index: 215743 (C4 (Web Text))

Max Activating Token Index: 742

Text #9

Max Range: 3.7988. Min Range: -3.7988

Max Act: 3.2880. Min Act: -0.0000

Data Index: 237475 (C4 (Web Text))

Max Activating Token Index: 517

Text #10

Max Range: 3.7988. Min Range: -3.7988

Max Act: 3.2173. Min Act: -0.0000

Data Index: 750372 (C4 (Web Text))

Max Activating Token Index: 214

Text #11

Max Range: 3.7988. Min Range: -3.7988

Max Act: 3.2110. Min Act: -0.0000

Data Index: 390383 (C4 (Web Text))

Max Activating Token Index: 322

Text #12

Max Range: 3.7988. Min Range: -3.7988

Max Act: 3.0542. Min Act: -0.0000

Data Index: 1216528 (C4 (Web Text))

Max Activating Token Index: 859

Text #13

Max Range: 3.7988. Min Range: -3.7988

Max Act: 3.0056. Min Act: -0.0000

Data Index: 781656 (C4 (Web Text))

Max Activating Token Index: 882

Text #14

Max Range: 3.7988. Min Range: -3.7988

Max Act: 2.8888. Min Act: -0.0000

Data Index: 1181211 (C4 (Web Text))

Max Activating Token Index: 219

Text #15

Max Range: 3.7988. Min Range: -3.7988

Max Act: 3.1837. Min Act: -0.0000

Data Index: 44418 (C4 (Web Text))

Max Activating Token Index: 679

Text #16

Max Range: 3.7988. Min Range: -3.7988

Max Act: 2.8841. Min Act: -0.0000

Data Index: 688435 (C4 (Web Text))

Max Activating Token Index: 156

Text #17

Max Range: 3.7988. Min Range: -3.7988

Max Act: 2.8219. Min Act: -0.0000

Data Index: 646796 (C4 (Web Text))

Max Activating Token Index: 943

Text #18

Max Range: 3.7988. Min Range: -3.7988

Max Act: 2.9925. Min Act: -0.0000

Data Index: 525224 (C4 (Web Text))

Max Activating Token Index: 390

Text #19

Max Range: 3.7988. Min Range: -3.7988

Max Act: 2.8418. Min Act: -0.0000

Data Index: 1181332 (C4 (Web Text))

Max Activating Token Index: 835