Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 430 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.1174. Min Act: -0.0004

Data Index: 346430 (C4 (Web Text))

Max Activating Token Index: 460

Text #1

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.0959. Min Act: -0.0004

Data Index: 501759 (C4 (Web Text))

Max Activating Token Index: 277

Text #2

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.0996. Min Act: -0.0004

Data Index: 252207 (C4 (Web Text))

Max Activating Token Index: 749

Text #3

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.0918. Min Act: -0.0003

Data Index: 250120 (C4 (Web Text))

Max Activating Token Index: 92

Text #4

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.0901. Min Act: -0.0003

Data Index: 120866 (C4 (Web Text))

Max Activating Token Index: 963

Text #5

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.0938. Min Act: -0.0003

Data Index: 856346 (C4 (Web Text))

Max Activating Token Index: 814

Text #6

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.0841. Min Act: -0.0003

Data Index: 1281562 (C4 (Web Text))

Max Activating Token Index: 588

Text #7

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.0821. Min Act: -0.0003

Data Index: 687787 (C4 (Web Text))

Max Activating Token Index: 188

Text #8

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.0835. Min Act: -0.0003

Data Index: 200370 (C4 (Web Text))

Max Activating Token Index: 207

Text #9

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.0789. Min Act: -0.0003

Data Index: 404594 (C4 (Web Text))

Max Activating Token Index: 215

Text #10

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.0785. Min Act: -0.0003

Data Index: 802185 (C4 (Web Text))

Max Activating Token Index: 119

Text #11

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.0784. Min Act: -0.0003

Data Index: 208964 (C4 (Web Text))

Max Activating Token Index: 28

Text #12

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.0780. Min Act: -0.0003

Data Index: 969275 (C4 (Web Text))

Max Activating Token Index: 851

Text #13

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.0750. Min Act: -0.0003

Data Index: 303372 (C4 (Web Text))

Max Activating Token Index: 750

Text #14

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.0748. Min Act: -0.0003

Data Index: 245404 (C4 (Web Text))

Max Activating Token Index: 830

Text #15

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.0745. Min Act: -0.0003

Data Index: 530153 (C4 (Web Text))

Max Activating Token Index: 222

Text #16

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.0728. Min Act: -0.0003

Data Index: 102561 (C4 (Web Text))

Max Activating Token Index: 237

Text #17

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.0720. Min Act: -0.0003

Data Index: 210666 (C4 (Web Text))

Max Activating Token Index: 116

Text #18

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.0730. Min Act: -0.0003

Data Index: 651953 (C4 (Web Text))

Max Activating Token Index: 299

Text #19

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.0761. Min Act: -0.0003

Data Index: 680267 (C4 (Web Text))

Max Activating Token Index: 377