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

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

Neuron 2025 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1536. Min Act: -0.0002

Data Index: 431630 (C4 (Web Text))

Max Activating Token Index: 242

Text #1

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1443. Min Act: -0.0002

Data Index: 1001250 (C4 (Web Text))

Max Activating Token Index: 658

Text #2

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1118. Min Act: -0.0002

Data Index: 495209 (C4 (Web Text))

Max Activating Token Index: 339

Text #3

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1101. Min Act: -0.0002

Data Index: 988123 (C4 (Web Text))

Max Activating Token Index: 186

Text #4

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1107. Min Act: -0.0002

Data Index: 906186 (C4 (Web Text))

Max Activating Token Index: 255

Text #5

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1059. Min Act: -0.0002

Data Index: 53383 (C4 (Web Text))

Max Activating Token Index: 93

Text #6

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1081. Min Act: -0.0002

Data Index: 1028756 (C4 (Web Text))

Max Activating Token Index: 357

Text #7

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.0983. Min Act: -0.0002

Data Index: 1125573 (C4 (Web Text))

Max Activating Token Index: 121

Text #8

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1100. Min Act: -0.0002

Data Index: 1100334 (C4 (Web Text))

Max Activating Token Index: 615

Text #9

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1038. Min Act: -0.0002

Data Index: 147837 (C4 (Web Text))

Max Activating Token Index: 5

Text #10

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.0815. Min Act: -0.0002

Data Index: 237092 (C4 (Web Text))

Max Activating Token Index: 145

Text #11

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.0966. Min Act: -0.0002

Data Index: 1218654 (C4 (Web Text))

Max Activating Token Index: 775

Text #12

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.0919. Min Act: -0.0002

Data Index: 1026635 (C4 (Web Text))

Max Activating Token Index: 179

Text #13

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.0984. Min Act: -0.0002

Data Index: 781517 (C4 (Web Text))

Max Activating Token Index: 487

Text #14

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1072. Min Act: -0.0002

Data Index: 144152 (C4 (Web Text))

Max Activating Token Index: 737

Text #15

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.0811. Min Act: -0.0002

Data Index: 115481 (C4 (Web Text))

Max Activating Token Index: 562

Text #16

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.0960. Min Act: -0.0002

Data Index: 81762 (C4 (Web Text))

Max Activating Token Index: 35

Text #17

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.0934. Min Act: -0.0002

Data Index: 700230 (C4 (Web Text))

Max Activating Token Index: 860

Text #18

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.0979. Min Act: -0.0002

Data Index: 194149 (C4 (Web Text))

Max Activating Token Index: 6

Text #19

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.0885. Min Act: -0.0002

Data Index: 61806 (C4 (Web Text))

Max Activating Token Index: 123