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

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

Neuron 2399 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8739. Min Range: -0.8739

Max Act: 0.8739. Min Act: -0.0002

Data Index: 1488212 (Python Code)

Max Activating Token Index: 248

Text #1

Max Range: 0.8739. Min Range: -0.8739

Max Act: 0.7868. Min Act: -0.0002

Data Index: 1454084 (Python Code)

Max Activating Token Index: 310

Text #2

Max Range: 0.8739. Min Range: -0.8739

Max Act: 0.7980. Min Act: -0.0002

Data Index: 1485862 (Python Code)

Max Activating Token Index: 721

Text #3

Max Range: 0.8739. Min Range: -0.8739

Max Act: 0.7942. Min Act: -0.0002

Data Index: 1475440 (Python Code)

Max Activating Token Index: 250

Text #4

Max Range: 0.8739. Min Range: -0.8739

Max Act: 0.7622. Min Act: -0.0002

Data Index: 1371730 (Python Code)

Max Activating Token Index: 326

Text #5

Max Range: 0.8739. Min Range: -0.8739

Max Act: 0.7271. Min Act: -0.0002

Data Index: 1642096 (Python Code)

Max Activating Token Index: 202

Text #6

Max Range: 0.8739. Min Range: -0.8739

Max Act: 0.7353. Min Act: -0.0002

Data Index: 1638757 (Python Code)

Max Activating Token Index: 242

Text #7

Max Range: 0.8739. Min Range: -0.8739

Max Act: 0.7160. Min Act: -0.0002

Data Index: 1599777 (Python Code)

Max Activating Token Index: 100

Text #8

Max Range: 0.8739. Min Range: -0.8739

Max Act: 0.7014. Min Act: -0.0002

Data Index: 1646129 (Python Code)

Max Activating Token Index: 978

Text #9

Max Range: 0.8739. Min Range: -0.8739

Max Act: 0.7166. Min Act: -0.0002

Data Index: 1379211 (Python Code)

Max Activating Token Index: 178

Text #10

Max Range: 0.8739. Min Range: -0.8739

Max Act: 0.6901. Min Act: -0.0002

Data Index: 1556026 (Python Code)

Max Activating Token Index: 164

Text #11

Max Range: 0.8739. Min Range: -0.8739

Max Act: 0.7133. Min Act: -0.0002

Data Index: 1410498 (Python Code)

Max Activating Token Index: 157

Text #12

Max Range: 0.8739. Min Range: -0.8739

Max Act: 0.6884. Min Act: -0.0002

Data Index: 1596897 (Python Code)

Max Activating Token Index: 175

Text #13

Max Range: 0.8739. Min Range: -0.8739

Max Act: 0.6758. Min Act: -0.0002

Data Index: 1407332 (Python Code)

Max Activating Token Index: 127

Text #14

Max Range: 0.8739. Min Range: -0.8739

Max Act: 0.6951. Min Act: -0.0002

Data Index: 1487553 (Python Code)

Max Activating Token Index: 291

Text #15

Max Range: 0.8739. Min Range: -0.8739

Max Act: 0.6607. Min Act: -0.0002

Data Index: 1481212 (Python Code)

Max Activating Token Index: 81

Text #16

Max Range: 0.8739. Min Range: -0.8739

Max Act: 0.6357. Min Act: -0.0002

Data Index: 1601982 (Python Code)

Max Activating Token Index: 775

Text #17

Max Range: 0.8739. Min Range: -0.8739

Max Act: 0.6406. Min Act: -0.0002

Data Index: 1656519 (Python Code)

Max Activating Token Index: 156

Text #18

Max Range: 0.8739. Min Range: -0.8739

Max Act: 0.6379. Min Act: -0.0002

Data Index: 1556211 (Python Code)

Max Activating Token Index: 170

Text #19

Max Range: 0.8739. Min Range: -0.8739

Max Act: 0.6330. Min Act: -0.0002

Data Index: 1645444 (Python Code)

Max Activating Token Index: 142