Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1413 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0193. Min Act: -0.0005

Data Index: 1191773 (C4 (Web Text))

Max Activating Token Index: 451

Text #1

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0192. Min Act: -0.0005

Data Index: 535071 (C4 (Web Text))

Max Activating Token Index: 724

Text #2

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0194. Min Act: -0.0005

Data Index: 131895 (C4 (Web Text))

Max Activating Token Index: 455

Text #3

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0183. Min Act: -0.0005

Data Index: 239919 (C4 (Web Text))

Max Activating Token Index: 45

Text #4

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0169. Min Act: -0.0005

Data Index: 479545 (C4 (Web Text))

Max Activating Token Index: 748

Text #5

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0129. Min Act: -0.0005

Data Index: 253991 (C4 (Web Text))

Max Activating Token Index: 710

Text #6

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0123. Min Act: -0.0005

Data Index: 625239 (C4 (Web Text))

Max Activating Token Index: 856

Text #7

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0119. Min Act: -0.0005

Data Index: 460248 (C4 (Web Text))

Max Activating Token Index: 521

Text #8

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0119. Min Act: -0.0005

Data Index: 38726 (C4 (Web Text))

Max Activating Token Index: 683

Text #9

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0116. Min Act: -0.0005

Data Index: 864908 (C4 (Web Text))

Max Activating Token Index: 679

Text #10

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0114. Min Act: -0.0005

Data Index: 1326701 (C4 (Web Text))

Max Activating Token Index: 928

Text #11

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0111. Min Act: -0.0005

Data Index: 1079471 (C4 (Web Text))

Max Activating Token Index: 617

Text #12

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0111. Min Act: -0.0005

Data Index: 484360 (C4 (Web Text))

Max Activating Token Index: 18

Text #13

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0108. Min Act: -0.0005

Data Index: 469958 (C4 (Web Text))

Max Activating Token Index: 964

Text #14

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0108. Min Act: -0.0005

Data Index: 485756 (C4 (Web Text))

Max Activating Token Index: 702

Text #15

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0103. Min Act: -0.0005

Data Index: 1606468 (Python Code)

Max Activating Token Index: 847

Text #16

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0107. Min Act: -0.0005

Data Index: 370464 (C4 (Web Text))

Max Activating Token Index: 620

Text #17

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0105. Min Act: -0.0005

Data Index: 917809 (C4 (Web Text))

Max Activating Token Index: 1011

Text #18

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0105. Min Act: -0.0005

Data Index: 931106 (C4 (Web Text))

Max Activating Token Index: 737

Text #19

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0106. Min Act: -0.0005

Data Index: 1636708 (Python Code)

Max Activating Token Index: 194