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

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

Neuron 4767 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2030. Min Range: -3.2030

Max Act: 3.2030. Min Act: -0.0001

Data Index: 31923 (C4 (Web Text))

Max Activating Token Index: 240

Text #1

Max Range: 3.2030. Min Range: -3.2030

Max Act: 3.0206. Min Act: -0.0001

Data Index: 1295427 (C4 (Web Text))

Max Activating Token Index: 246

Text #2

Max Range: 3.2030. Min Range: -3.2030

Max Act: 3.0343. Min Act: -0.0001

Data Index: 516467 (C4 (Web Text))

Max Activating Token Index: 652

Text #3

Max Range: 3.2030. Min Range: -3.2030

Max Act: 2.8739. Min Act: -0.0001

Data Index: 942218 (C4 (Web Text))

Max Activating Token Index: 422

Text #4

Max Range: 3.2030. Min Range: -3.2030

Max Act: 2.6757. Min Act: -0.0001

Data Index: 515320 (C4 (Web Text))

Max Activating Token Index: 445

Text #5

Max Range: 3.2030. Min Range: -3.2030

Max Act: 2.5994. Min Act: -0.0001

Data Index: 408218 (C4 (Web Text))

Max Activating Token Index: 644

Text #6

Max Range: 3.2030. Min Range: -3.2030

Max Act: 2.2804. Min Act: -0.0001

Data Index: 974757 (C4 (Web Text))

Max Activating Token Index: 232

Text #7

Max Range: 3.2030. Min Range: -3.2030

Max Act: 2.5716. Min Act: -0.0001

Data Index: 1211681 (C4 (Web Text))

Max Activating Token Index: 247

Text #8

Max Range: 3.2030. Min Range: -3.2030

Max Act: 2.4883. Min Act: -0.0001

Data Index: 1168429 (C4 (Web Text))

Max Activating Token Index: 583

Text #9

Max Range: 3.2030. Min Range: -3.2030

Max Act: 2.4406. Min Act: -0.0001

Data Index: 204757 (C4 (Web Text))

Max Activating Token Index: 23

Text #10

Max Range: 3.2030. Min Range: -3.2030

Max Act: 2.2931. Min Act: -0.0001

Data Index: 1211045 (C4 (Web Text))

Max Activating Token Index: 488

Text #11

Max Range: 3.2030. Min Range: -3.2030

Max Act: 2.3412. Min Act: -0.0001

Data Index: 698256 (C4 (Web Text))

Max Activating Token Index: 737

Text #12

Max Range: 3.2030. Min Range: -3.2030

Max Act: 2.3702. Min Act: -0.0001

Data Index: 1090412 (C4 (Web Text))

Max Activating Token Index: 318

Text #13

Max Range: 3.2030. Min Range: -3.2030

Max Act: 2.4080. Min Act: -0.0001

Data Index: 1221239 (C4 (Web Text))

Max Activating Token Index: 463

Text #14

Max Range: 3.2030. Min Range: -3.2030

Max Act: 2.0467. Min Act: -0.0001

Data Index: 772523 (C4 (Web Text))

Max Activating Token Index: 816

Text #15

Max Range: 3.2030. Min Range: -3.2030

Max Act: 2.1148. Min Act: -0.0001

Data Index: 189414 (C4 (Web Text))

Max Activating Token Index: 272

Text #16

Max Range: 3.2030. Min Range: -3.2030

Max Act: 2.1587. Min Act: -0.0001

Data Index: 1243544 (C4 (Web Text))

Max Activating Token Index: 727

Text #17

Max Range: 3.2030. Min Range: -3.2030

Max Act: 2.4176. Min Act: -0.0001

Data Index: 1160264 (C4 (Web Text))

Max Activating Token Index: 108

Text #18

Max Range: 3.2030. Min Range: -3.2030

Max Act: 2.1569. Min Act: -0.0001

Data Index: 511313 (C4 (Web Text))

Max Activating Token Index: 796

Text #19

Max Range: 3.2030. Min Range: -3.2030

Max Act: 1.8329. Min Act: -0.0001

Data Index: 519483 (C4 (Web Text))

Max Activating Token Index: 260