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

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

Neuron 172 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8655. Min Range: -1.8655

Max Act: 1.8150. Min Act: -0.0000

Data Index: 827793 (C4 (Web Text))

Max Activating Token Index: 127

Text #1

Max Range: 1.8655. Min Range: -1.8655

Max Act: 1.8655. Min Act: -0.0000

Data Index: 947029 (C4 (Web Text))

Max Activating Token Index: 662

Text #2

Max Range: 1.8655. Min Range: -1.8655

Max Act: 1.6749. Min Act: -0.0000

Data Index: 720515 (C4 (Web Text))

Max Activating Token Index: 697

Text #3

Max Range: 1.8655. Min Range: -1.8655

Max Act: 1.7379. Min Act: -0.0000

Data Index: 343356 (C4 (Web Text))

Max Activating Token Index: 546

Text #4

Max Range: 1.8655. Min Range: -1.8655

Max Act: 1.7168. Min Act: -0.0000

Data Index: 295259 (C4 (Web Text))

Max Activating Token Index: 258

Text #5

Max Range: 1.8655. Min Range: -1.8655

Max Act: 1.6265. Min Act: -0.0000

Data Index: 580206 (C4 (Web Text))

Max Activating Token Index: 574

Text #6

Max Range: 1.8655. Min Range: -1.8655

Max Act: 1.5737. Min Act: -0.0000

Data Index: 414136 (C4 (Web Text))

Max Activating Token Index: 896

Text #7

Max Range: 1.8655. Min Range: -1.8655

Max Act: 1.4615. Min Act: -0.0000

Data Index: 195376 (C4 (Web Text))

Max Activating Token Index: 270

Text #8

Max Range: 1.8655. Min Range: -1.8655

Max Act: 1.3158. Min Act: -0.0000

Data Index: 1057605 (C4 (Web Text))

Max Activating Token Index: 778

Text #9

Max Range: 1.8655. Min Range: -1.8655

Max Act: 1.5777. Min Act: -0.0000

Data Index: 1074607 (C4 (Web Text))

Max Activating Token Index: 511

Text #10

Max Range: 1.8655. Min Range: -1.8655

Max Act: 1.5133. Min Act: -0.0000

Data Index: 734221 (C4 (Web Text))

Max Activating Token Index: 665

Text #11

Max Range: 1.8655. Min Range: -1.8655

Max Act: 1.5976. Min Act: -0.0000

Data Index: 787905 (C4 (Web Text))

Max Activating Token Index: 918

Text #12

Max Range: 1.8655. Min Range: -1.8655

Max Act: 1.5280. Min Act: -0.0000

Data Index: 837099 (C4 (Web Text))

Max Activating Token Index: 230

Text #13

Max Range: 1.8655. Min Range: -1.8655

Max Act: 1.4693. Min Act: -0.0000

Data Index: 413796 (C4 (Web Text))

Max Activating Token Index: 219

Text #14

Max Range: 1.8655. Min Range: -1.8655

Max Act: 1.4077. Min Act: -0.0001

Data Index: 847489 (C4 (Web Text))

Max Activating Token Index: 806

Text #15

Max Range: 1.8655. Min Range: -1.8655

Max Act: 1.4071. Min Act: -0.0000

Data Index: 1124631 (C4 (Web Text))

Max Activating Token Index: 616

Text #16

Max Range: 1.8655. Min Range: -1.8655

Max Act: 1.4615. Min Act: -0.0000

Data Index: 116285 (C4 (Web Text))

Max Activating Token Index: 757

Text #17

Max Range: 1.8655. Min Range: -1.8655

Max Act: 1.4412. Min Act: -0.0000

Data Index: 895381 (C4 (Web Text))

Max Activating Token Index: 80

Text #18

Max Range: 1.8655. Min Range: -1.8655

Max Act: 1.3757. Min Act: -0.0000

Data Index: 1215806 (C4 (Web Text))

Max Activating Token Index: 493

Text #19

Max Range: 1.8655. Min Range: -1.8655

Max Act: 1.4464. Min Act: -0.0000

Data Index: 210975 (C4 (Web Text))

Max Activating Token Index: 182