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

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

Neuron 1632 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0114. Min Range: -1.0114

Max Act: 1.0053. Min Act: -0.0000

Data Index: 382200 (C4 (Web Text))

Max Activating Token Index: 1018

Text #1

Max Range: 1.0114. Min Range: -1.0114

Max Act: 0.9396. Min Act: -0.0000

Data Index: 1286318 (C4 (Web Text))

Max Activating Token Index: 787

Text #2

Max Range: 1.0114. Min Range: -1.0114

Max Act: 0.9468. Min Act: -0.0000

Data Index: 505383 (C4 (Web Text))

Max Activating Token Index: 612

Text #3

Max Range: 1.0114. Min Range: -1.0114

Max Act: 0.9208. Min Act: -0.0000

Data Index: 859254 (C4 (Web Text))

Max Activating Token Index: 361

Text #4

Max Range: 1.0114. Min Range: -1.0114

Max Act: 1.0114. Min Act: -0.0000

Data Index: 1342846 (C4 (Web Text))

Max Activating Token Index: 270

Text #5

Max Range: 1.0114. Min Range: -1.0114

Max Act: 0.9203. Min Act: -0.0000

Data Index: 1046659 (C4 (Web Text))

Max Activating Token Index: 522

Text #6

Max Range: 1.0114. Min Range: -1.0114

Max Act: 0.9002. Min Act: -0.0000

Data Index: 552951 (C4 (Web Text))

Max Activating Token Index: 77

Text #7

Max Range: 1.0114. Min Range: -1.0114

Max Act: 0.9106. Min Act: -0.0000

Data Index: 442868 (C4 (Web Text))

Max Activating Token Index: 778

Text #8

Max Range: 1.0114. Min Range: -1.0114

Max Act: 0.8624. Min Act: -0.0000

Data Index: 837318 (C4 (Web Text))

Max Activating Token Index: 970

Text #9

Max Range: 1.0114. Min Range: -1.0114

Max Act: 0.8563. Min Act: -0.0000

Data Index: 1219788 (C4 (Web Text))

Max Activating Token Index: 254

Text #10

Max Range: 1.0114. Min Range: -1.0114

Max Act: 0.8966. Min Act: -0.0000

Data Index: 1161732 (C4 (Web Text))

Max Activating Token Index: 155

Text #11

Max Range: 1.0114. Min Range: -1.0114

Max Act: 0.8915. Min Act: -0.0000

Data Index: 134941 (C4 (Web Text))

Max Activating Token Index: 745

Text #12

Max Range: 1.0114. Min Range: -1.0114

Max Act: 0.8659. Min Act: -0.0000

Data Index: 1405845 (Python Code)

Max Activating Token Index: 74

Text #13

Max Range: 1.0114. Min Range: -1.0114

Max Act: 0.8582. Min Act: -0.0000

Data Index: 1819 (C4 (Web Text))

Max Activating Token Index: 622

Text #14

Max Range: 1.0114. Min Range: -1.0114

Max Act: 0.8254. Min Act: -0.0000

Data Index: 685949 (C4 (Web Text))

Max Activating Token Index: 631

Text #15

Max Range: 1.0114. Min Range: -1.0114

Max Act: 0.8746. Min Act: -0.0000

Data Index: 950309 (C4 (Web Text))

Max Activating Token Index: 636

Text #16

Max Range: 1.0114. Min Range: -1.0114

Max Act: 0.8273. Min Act: -0.0000

Data Index: 158044 (C4 (Web Text))

Max Activating Token Index: 831

Text #17

Max Range: 1.0114. Min Range: -1.0114

Max Act: 0.8803. Min Act: -0.0000

Data Index: 459016 (C4 (Web Text))

Max Activating Token Index: 100

Text #18

Max Range: 1.0114. Min Range: -1.0114

Max Act: 0.8677. Min Act: -0.0000

Data Index: 1125965 (C4 (Web Text))

Max Activating Token Index: 260

Text #19

Max Range: 1.0114. Min Range: -1.0114

Max Act: 0.9449. Min Act: -0.0000

Data Index: 1313173 (C4 (Web Text))

Max Activating Token Index: 869