Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3221 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.0119. Min Range: -2.0119

Max Act: 2.0119. Min Act: -0.0000

Data Index: 682349 (C4 (Web Text))

Max Activating Token Index: 1006

Text #1

Max Range: 2.0119. Min Range: -2.0119

Max Act: 1.9844. Min Act: -0.0000

Data Index: 917754 (C4 (Web Text))

Max Activating Token Index: 258

Text #2

Max Range: 2.0119. Min Range: -2.0119

Max Act: 1.7094. Min Act: -0.0000

Data Index: 1119621 (C4 (Web Text))

Max Activating Token Index: 735

Text #3

Max Range: 2.0119. Min Range: -2.0119

Max Act: 1.7186. Min Act: -0.0000

Data Index: 109408 (C4 (Web Text))

Max Activating Token Index: 823

Text #4

Max Range: 2.0119. Min Range: -2.0119

Max Act: 1.6805. Min Act: -0.0000

Data Index: 859158 (C4 (Web Text))

Max Activating Token Index: 111

Text #5

Max Range: 2.0119. Min Range: -2.0119

Max Act: 1.5818. Min Act: -0.0000

Data Index: 397722 (C4 (Web Text))

Max Activating Token Index: 752

Text #6

Max Range: 2.0119. Min Range: -2.0119

Max Act: 1.5246. Min Act: -0.0000

Data Index: 142645 (C4 (Web Text))

Max Activating Token Index: 341

Text #7

Max Range: 2.0119. Min Range: -2.0119

Max Act: 1.4966. Min Act: -0.0000

Data Index: 907755 (C4 (Web Text))

Max Activating Token Index: 339

Text #8

Max Range: 2.0119. Min Range: -2.0119

Max Act: 1.5885. Min Act: -0.0000

Data Index: 1207309 (C4 (Web Text))

Max Activating Token Index: 980

Text #9

Max Range: 2.0119. Min Range: -2.0119

Max Act: 1.4833. Min Act: -0.0000

Data Index: 595541 (C4 (Web Text))

Max Activating Token Index: 402

Text #10

Max Range: 2.0119. Min Range: -2.0119

Max Act: 1.4445. Min Act: -0.0000

Data Index: 1263466 (C4 (Web Text))

Max Activating Token Index: 297

Text #11

Max Range: 2.0119. Min Range: -2.0119

Max Act: 1.4596. Min Act: -0.0000

Data Index: 244116 (C4 (Web Text))

Max Activating Token Index: 101

Text #12

Max Range: 2.0119. Min Range: -2.0119

Max Act: 1.5222. Min Act: -0.0000

Data Index: 176665 (C4 (Web Text))

Max Activating Token Index: 911

Text #13

Max Range: 2.0119. Min Range: -2.0119

Max Act: 1.4304. Min Act: -0.0000

Data Index: 73726 (C4 (Web Text))

Max Activating Token Index: 363

Text #14

Max Range: 2.0119. Min Range: -2.0119

Max Act: 1.3468. Min Act: -0.0000

Data Index: 1253886 (C4 (Web Text))

Max Activating Token Index: 701

Text #15

Max Range: 2.0119. Min Range: -2.0119

Max Act: 1.4104. Min Act: -0.0000

Data Index: 907441 (C4 (Web Text))

Max Activating Token Index: 468

Text #16

Max Range: 2.0119. Min Range: -2.0119

Max Act: 1.4139. Min Act: -0.0000

Data Index: 1247064 (C4 (Web Text))

Max Activating Token Index: 394

Text #17

Max Range: 2.0119. Min Range: -2.0119

Max Act: 1.4104. Min Act: -0.0000

Data Index: 862017 (C4 (Web Text))

Max Activating Token Index: 269

Text #18

Max Range: 2.0119. Min Range: -2.0119

Max Act: 1.3178. Min Act: -0.0000

Data Index: 777454 (C4 (Web Text))

Max Activating Token Index: 95

Text #19

Max Range: 2.0119. Min Range: -2.0119

Max Act: 1.3734. Min Act: -0.0000

Data Index: 549971 (C4 (Web Text))

Max Activating Token Index: 713