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

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

Neuron 3598 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1581. Min Range: -1.1581

Max Act: 1.0399. Min Act: -0.0002

Data Index: 781514 (C4 (Web Text))

Max Activating Token Index: 43

Text #1

Max Range: 1.1581. Min Range: -1.1581

Max Act: 1.0711. Min Act: -0.0002

Data Index: 808590 (C4 (Web Text))

Max Activating Token Index: 188

Text #2

Max Range: 1.1581. Min Range: -1.1581

Max Act: 1.0986. Min Act: -0.0002

Data Index: 3160 (C4 (Web Text))

Max Activating Token Index: 197

Text #3

Max Range: 1.1581. Min Range: -1.1581

Max Act: 0.9809. Min Act: -0.0002

Data Index: 397721 (C4 (Web Text))

Max Activating Token Index: 197

Text #4

Max Range: 1.1581. Min Range: -1.1581

Max Act: 1.1581. Min Act: -0.0002

Data Index: 1143330 (C4 (Web Text))

Max Activating Token Index: 757

Text #5

Max Range: 1.1581. Min Range: -1.1581

Max Act: 0.8867. Min Act: -0.0002

Data Index: 640989 (C4 (Web Text))

Max Activating Token Index: 281

Text #6

Max Range: 1.1581. Min Range: -1.1581

Max Act: 0.9540. Min Act: -0.0002

Data Index: 330406 (C4 (Web Text))

Max Activating Token Index: 582

Text #7

Max Range: 1.1581. Min Range: -1.1581

Max Act: 0.9070. Min Act: -0.0002

Data Index: 526246 (C4 (Web Text))

Max Activating Token Index: 682

Text #8

Max Range: 1.1581. Min Range: -1.1581

Max Act: 1.0714. Min Act: -0.0002

Data Index: 219844 (C4 (Web Text))

Max Activating Token Index: 267

Text #9

Max Range: 1.1581. Min Range: -1.1581

Max Act: 0.8792. Min Act: -0.0002

Data Index: 593657 (C4 (Web Text))

Max Activating Token Index: 154

Text #10

Max Range: 1.1581. Min Range: -1.1581

Max Act: 0.8997. Min Act: -0.0002

Data Index: 346212 (C4 (Web Text))

Max Activating Token Index: 343

Text #11

Max Range: 1.1581. Min Range: -1.1581

Max Act: 0.8853. Min Act: -0.0002

Data Index: 676764 (C4 (Web Text))

Max Activating Token Index: 535

Text #12

Max Range: 1.1581. Min Range: -1.1581

Max Act: 0.9422. Min Act: -0.0002

Data Index: 616891 (C4 (Web Text))

Max Activating Token Index: 217

Text #13

Max Range: 1.1581. Min Range: -1.1581

Max Act: 0.9003. Min Act: -0.0002

Data Index: 779300 (C4 (Web Text))

Max Activating Token Index: 351

Text #14

Max Range: 1.1581. Min Range: -1.1581

Max Act: 1.0181. Min Act: -0.0002

Data Index: 1122580 (C4 (Web Text))

Max Activating Token Index: 248

Text #15

Max Range: 1.1581. Min Range: -1.1581

Max Act: 0.8571. Min Act: -0.0002

Data Index: 1138329 (C4 (Web Text))

Max Activating Token Index: 735

Text #16

Max Range: 1.1581. Min Range: -1.1581

Max Act: 0.8771. Min Act: -0.0002

Data Index: 495934 (C4 (Web Text))

Max Activating Token Index: 198

Text #17

Max Range: 1.1581. Min Range: -1.1581

Max Act: 0.8800. Min Act: -0.0002

Data Index: 1190187 (C4 (Web Text))

Max Activating Token Index: 182

Text #18

Max Range: 1.1581. Min Range: -1.1581

Max Act: 0.7670. Min Act: -0.0002

Data Index: 1026228 (C4 (Web Text))

Max Activating Token Index: 149

Text #19

Max Range: 1.1581. Min Range: -1.1581

Max Act: 0.8947. Min Act: -0.0002

Data Index: 1299556 (C4 (Web Text))

Max Activating Token Index: 563