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

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

Neuron 1947 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: 0.9247. Min Range: -0.9247

Max Act: 0.9247. Min Act: -0.0000

Data Index: 181433 (C4 (Web Text))

Max Activating Token Index: 541

Text #1

Max Range: 0.9247. Min Range: -0.9247

Max Act: 0.7117. Min Act: -0.0000

Data Index: 171804 (C4 (Web Text))

Max Activating Token Index: 187

Text #2

Max Range: 0.9247. Min Range: -0.9247

Max Act: 0.6049. Min Act: -0.0000

Data Index: 1552243 (Python Code)

Max Activating Token Index: 118

Text #3

Max Range: 0.9247. Min Range: -0.9247

Max Act: 0.5952. Min Act: -0.0000

Data Index: 1495952 (Python Code)

Max Activating Token Index: 209

Text #4

Max Range: 0.9247. Min Range: -0.9247

Max Act: 0.5737. Min Act: -0.0000

Data Index: 163818 (C4 (Web Text))

Max Activating Token Index: 651

Text #5

Max Range: 0.9247. Min Range: -0.9247

Max Act: 0.6014. Min Act: -0.0000

Data Index: 1200202 (C4 (Web Text))

Max Activating Token Index: 14

Text #6

Max Range: 0.9247. Min Range: -0.9247

Max Act: 0.5632. Min Act: -0.0000

Data Index: 1500705 (Python Code)

Max Activating Token Index: 161

Text #7

Max Range: 0.9247. Min Range: -0.9247

Max Act: 0.5098. Min Act: -0.0000

Data Index: 901693 (C4 (Web Text))

Max Activating Token Index: 665

Text #8

Max Range: 0.9247. Min Range: -0.9247

Max Act: 0.5129. Min Act: -0.0000

Data Index: 633701 (C4 (Web Text))

Max Activating Token Index: 18

Text #9

Max Range: 0.9247. Min Range: -0.9247

Max Act: 0.5656. Min Act: -0.0000

Data Index: 1475454 (Python Code)

Max Activating Token Index: 200

Text #10

Max Range: 0.9247. Min Range: -0.9247

Max Act: 0.4958. Min Act: -0.0000

Data Index: 503834 (C4 (Web Text))

Max Activating Token Index: 178

Text #11

Max Range: 0.9247. Min Range: -0.9247

Max Act: 0.4701. Min Act: -0.0000

Data Index: 127613 (C4 (Web Text))

Max Activating Token Index: 330

Text #12

Max Range: 0.9247. Min Range: -0.9247

Max Act: 0.4871. Min Act: -0.0000

Data Index: 1368258 (Python Code)

Max Activating Token Index: 802

Text #13

Max Range: 0.9247. Min Range: -0.9247

Max Act: 0.4923. Min Act: -0.0000

Data Index: 1606905 (Python Code)

Max Activating Token Index: 1019

Text #14

Max Range: 0.9247. Min Range: -0.9247

Max Act: 0.5017. Min Act: -0.0000

Data Index: 1138015 (C4 (Web Text))

Max Activating Token Index: 595

Text #15

Max Range: 0.9247. Min Range: -0.9247

Max Act: 0.4965. Min Act: -0.0000

Data Index: 1141576 (C4 (Web Text))

Max Activating Token Index: 705

Text #16

Max Range: 0.9247. Min Range: -0.9247

Max Act: 0.4722. Min Act: -0.0000

Data Index: 345055 (C4 (Web Text))

Max Activating Token Index: 10

Text #17

Max Range: 0.9247. Min Range: -0.9247

Max Act: 0.4717. Min Act: -0.0000

Data Index: 1380596 (Python Code)

Max Activating Token Index: 812

Text #18

Max Range: 0.9247. Min Range: -0.9247

Max Act: 0.4855. Min Act: -0.0000

Data Index: 1060059 (C4 (Web Text))

Max Activating Token Index: 590

Text #19

Max Range: 0.9247. Min Range: -0.9247

Max Act: 0.4714. Min Act: -0.0000

Data Index: 1414828 (Python Code)

Max Activating Token Index: 344