Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2320 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7193. Min Range: -0.7193

Max Act: 0.7006. Min Act: -0.0000

Data Index: 1239491 (C4 (Web Text))

Max Activating Token Index: 180

Text #1

Max Range: 0.7193. Min Range: -0.7193

Max Act: 0.7193. Min Act: -0.0000

Data Index: 320983 (C4 (Web Text))

Max Activating Token Index: 274

Text #2

Max Range: 0.7193. Min Range: -0.7193

Max Act: 0.6681. Min Act: -0.0000

Data Index: 522365 (C4 (Web Text))

Max Activating Token Index: 304

Text #3

Max Range: 0.7193. Min Range: -0.7193

Max Act: 0.5865. Min Act: -0.0000

Data Index: 111464 (C4 (Web Text))

Max Activating Token Index: 167

Text #4

Max Range: 0.7193. Min Range: -0.7193

Max Act: 0.5615. Min Act: -0.0000

Data Index: 805088 (C4 (Web Text))

Max Activating Token Index: 240

Text #5

Max Range: 0.7193. Min Range: -0.7193

Max Act: 0.5831. Min Act: -0.0000

Data Index: 837321 (C4 (Web Text))

Max Activating Token Index: 681

Text #6

Max Range: 0.7193. Min Range: -0.7193

Max Act: 0.6062. Min Act: -0.0000

Data Index: 852923 (C4 (Web Text))

Max Activating Token Index: 242

Text #7

Max Range: 0.7193. Min Range: -0.7193

Max Act: 0.6186. Min Act: -0.0000

Data Index: 448755 (C4 (Web Text))

Max Activating Token Index: 739

Text #8

Max Range: 0.7193. Min Range: -0.7193

Max Act: 0.5826. Min Act: -0.0000

Data Index: 1237982 (C4 (Web Text))

Max Activating Token Index: 439

Text #9

Max Range: 0.7193. Min Range: -0.7193

Max Act: 0.5786. Min Act: -0.0000

Data Index: 1011406 (C4 (Web Text))

Max Activating Token Index: 47

Text #10

Max Range: 0.7193. Min Range: -0.7193

Max Act: 0.5713. Min Act: -0.0000

Data Index: 512176 (C4 (Web Text))

Max Activating Token Index: 741

Text #11

Max Range: 0.7193. Min Range: -0.7193

Max Act: 0.5672. Min Act: -0.0000

Data Index: 87690 (C4 (Web Text))

Max Activating Token Index: 228

Text #12

Max Range: 0.7193. Min Range: -0.7193

Max Act: 0.5144. Min Act: -0.0000

Data Index: 148384 (C4 (Web Text))

Max Activating Token Index: 850

Text #13

Max Range: 0.7193. Min Range: -0.7193

Max Act: 0.5437. Min Act: -0.0000

Data Index: 1207299 (C4 (Web Text))

Max Activating Token Index: 224

Text #14

Max Range: 0.7193. Min Range: -0.7193

Max Act: 0.4840. Min Act: -0.0000

Data Index: 510696 (C4 (Web Text))

Max Activating Token Index: 955

Text #15

Max Range: 0.7193. Min Range: -0.7193

Max Act: 0.5013. Min Act: -0.0000

Data Index: 833996 (C4 (Web Text))

Max Activating Token Index: 442

Text #16

Max Range: 0.7193. Min Range: -0.7193

Max Act: 0.5012. Min Act: -0.0000

Data Index: 705731 (C4 (Web Text))

Max Activating Token Index: 962

Text #17

Max Range: 0.7193. Min Range: -0.7193

Max Act: 0.5188. Min Act: -0.0000

Data Index: 915069 (C4 (Web Text))

Max Activating Token Index: 504

Text #18

Max Range: 0.7193. Min Range: -0.7193

Max Act: 0.5099. Min Act: -0.0000

Data Index: 1089995 (C4 (Web Text))

Max Activating Token Index: 985

Text #19

Max Range: 0.7193. Min Range: -0.7193

Max Act: 0.5136. Min Act: -0.0000

Data Index: 365699 (C4 (Web Text))

Max Activating Token Index: 570