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

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

Neuron 518 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8156. Min Range: -1.8156

Max Act: 1.8156. Min Act: -0.0001

Data Index: 479038 (C4 (Web Text))

Max Activating Token Index: 314

Text #1

Max Range: 1.8156. Min Range: -1.8156

Max Act: 1.2758. Min Act: -0.0001

Data Index: 1110336 (C4 (Web Text))

Max Activating Token Index: 340

Text #2

Max Range: 1.8156. Min Range: -1.8156

Max Act: 1.1125. Min Act: -0.0001

Data Index: 645636 (C4 (Web Text))

Max Activating Token Index: 595

Text #3

Max Range: 1.8156. Min Range: -1.8156

Max Act: 1.0470. Min Act: -0.0001

Data Index: 1177234 (C4 (Web Text))

Max Activating Token Index: 615

Text #4

Max Range: 1.8156. Min Range: -1.8156

Max Act: 1.0154. Min Act: -0.0001

Data Index: 365108 (C4 (Web Text))

Max Activating Token Index: 756

Text #5

Max Range: 1.8156. Min Range: -1.8156

Max Act: 1.1286. Min Act: -0.0001

Data Index: 343465 (C4 (Web Text))

Max Activating Token Index: 356

Text #6

Max Range: 1.8156. Min Range: -1.8156

Max Act: 1.0838. Min Act: -0.0001

Data Index: 684539 (C4 (Web Text))

Max Activating Token Index: 682

Text #7

Max Range: 1.8156. Min Range: -1.8156

Max Act: 1.0686. Min Act: -0.0001

Data Index: 955468 (C4 (Web Text))

Max Activating Token Index: 41

Text #8

Max Range: 1.8156. Min Range: -1.8156

Max Act: 0.9732. Min Act: -0.0001

Data Index: 872077 (C4 (Web Text))

Max Activating Token Index: 906

Text #9

Max Range: 1.8156. Min Range: -1.8156

Max Act: 1.0174. Min Act: -0.0001

Data Index: 976455 (C4 (Web Text))

Max Activating Token Index: 380

Text #10

Max Range: 1.8156. Min Range: -1.8156

Max Act: 0.9334. Min Act: -0.0001

Data Index: 619085 (C4 (Web Text))

Max Activating Token Index: 610

Text #11

Max Range: 1.8156. Min Range: -1.8156

Max Act: 0.9073. Min Act: -0.0001

Data Index: 1021804 (C4 (Web Text))

Max Activating Token Index: 848

Text #12

Max Range: 1.8156. Min Range: -1.8156

Max Act: 0.9404. Min Act: -0.0001

Data Index: 875385 (C4 (Web Text))

Max Activating Token Index: 391

Text #13

Max Range: 1.8156. Min Range: -1.8156

Max Act: 1.0624. Min Act: -0.0001

Data Index: 1243399 (C4 (Web Text))

Max Activating Token Index: 133

Text #14

Max Range: 1.8156. Min Range: -1.8156

Max Act: 0.9578. Min Act: -0.0001

Data Index: 1048574 (C4 (Web Text))

Max Activating Token Index: 424

Text #15

Max Range: 1.8156. Min Range: -1.8156

Max Act: 0.9253. Min Act: -0.0001

Data Index: 317817 (C4 (Web Text))

Max Activating Token Index: 438

Text #16

Max Range: 1.8156. Min Range: -1.8156

Max Act: 1.0030. Min Act: -0.0001

Data Index: 752061 (C4 (Web Text))

Max Activating Token Index: 427

Text #17

Max Range: 1.8156. Min Range: -1.8156

Max Act: 1.0718. Min Act: -0.0001

Data Index: 1221197 (C4 (Web Text))

Max Activating Token Index: 640

Text #18

Max Range: 1.8156. Min Range: -1.8156

Max Act: 0.8590. Min Act: -0.0001

Data Index: 696582 (C4 (Web Text))

Max Activating Token Index: 213

Text #19

Max Range: 1.8156. Min Range: -1.8156

Max Act: 0.8918. Min Act: -0.0001

Data Index: 476713 (C4 (Web Text))

Max Activating Token Index: 796