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

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

Neuron 513 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: 2.3067. Min Range: -2.3067

Max Act: 2.3067. Min Act: -0.0000

Data Index: 1563276 (Python Code)

Max Activating Token Index: 175

Text #1

Max Range: 2.3067. Min Range: -2.3067

Max Act: 2.1943. Min Act: -0.0000

Data Index: 1422434 (Python Code)

Max Activating Token Index: 332

Text #2

Max Range: 2.3067. Min Range: -2.3067

Max Act: 1.9662. Min Act: -0.0000

Data Index: 1519529 (Python Code)

Max Activating Token Index: 169

Text #3

Max Range: 2.3067. Min Range: -2.3067

Max Act: 1.8128. Min Act: -0.0000

Data Index: 1563310 (Python Code)

Max Activating Token Index: 295

Text #4

Max Range: 2.3067. Min Range: -2.3067

Max Act: 1.7358. Min Act: -0.0000

Data Index: 1417192 (Python Code)

Max Activating Token Index: 997

Text #5

Max Range: 2.3067. Min Range: -2.3067

Max Act: 1.9001. Min Act: -0.0000

Data Index: 1623850 (Python Code)

Max Activating Token Index: 386

Text #6

Max Range: 2.3067. Min Range: -2.3067

Max Act: 1.6146. Min Act: -0.0000

Data Index: 1400853 (Python Code)

Max Activating Token Index: 104

Text #7

Max Range: 2.3067. Min Range: -2.3067

Max Act: 1.5987. Min Act: -0.0000

Data Index: 1615523 (Python Code)

Max Activating Token Index: 590

Text #8

Max Range: 2.3067. Min Range: -2.3067

Max Act: 1.5211. Min Act: -0.0000

Data Index: 1615467 (Python Code)

Max Activating Token Index: 400

Text #9

Max Range: 2.3067. Min Range: -2.3067

Max Act: 1.5164. Min Act: -0.0000

Data Index: 1380818 (Python Code)

Max Activating Token Index: 233

Text #10

Max Range: 2.3067. Min Range: -2.3067

Max Act: 1.6661. Min Act: -0.0000

Data Index: 1422253 (Python Code)

Max Activating Token Index: 543

Text #11

Max Range: 2.3067. Min Range: -2.3067

Max Act: 1.5877. Min Act: -0.0000

Data Index: 1614014 (Python Code)

Max Activating Token Index: 221

Text #12

Max Range: 2.3067. Min Range: -2.3067

Max Act: 1.5366. Min Act: -0.0000

Data Index: 1541151 (Python Code)

Max Activating Token Index: 286

Text #13

Max Range: 2.3067. Min Range: -2.3067

Max Act: 1.5193. Min Act: -0.0000

Data Index: 1484441 (Python Code)

Max Activating Token Index: 554

Text #14

Max Range: 2.3067. Min Range: -2.3067

Max Act: 1.3514. Min Act: -0.0000

Data Index: 1556935 (Python Code)

Max Activating Token Index: 467

Text #15

Max Range: 2.3067. Min Range: -2.3067

Max Act: 1.4887. Min Act: -0.0000

Data Index: 1549957 (Python Code)

Max Activating Token Index: 60

Text #16

Max Range: 2.3067. Min Range: -2.3067

Max Act: 1.4031. Min Act: -0.0000

Data Index: 1629792 (Python Code)

Max Activating Token Index: 139

Text #17

Max Range: 2.3067. Min Range: -2.3067

Max Act: 1.3509. Min Act: -0.0000

Data Index: 1555409 (Python Code)

Max Activating Token Index: 114

Text #18

Max Range: 2.3067. Min Range: -2.3067

Max Act: 1.4002. Min Act: -0.0000

Data Index: 1392980 (Python Code)

Max Activating Token Index: 322

Text #19

Max Range: 2.3067. Min Range: -2.3067

Max Act: 1.3798. Min Act: -0.0000

Data Index: 1584182 (Python Code)

Max Activating Token Index: 426