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

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

Neuron 2599 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9095. Min Range: -0.9095

Max Act: 0.9095. Min Act: -0.0001

Data Index: 1384924 (Python Code)

Max Activating Token Index: 409

Text #1

Max Range: 0.9095. Min Range: -0.9095

Max Act: 0.8268. Min Act: -0.0001

Data Index: 381356 (C4 (Web Text))

Max Activating Token Index: 587

Text #2

Max Range: 0.9095. Min Range: -0.9095

Max Act: 0.6983. Min Act: -0.0000

Data Index: 658328 (C4 (Web Text))

Max Activating Token Index: 887

Text #3

Max Range: 0.9095. Min Range: -0.9095

Max Act: 0.7955. Min Act: -0.0000

Data Index: 363437 (C4 (Web Text))

Max Activating Token Index: 196

Text #4

Max Range: 0.9095. Min Range: -0.9095

Max Act: 0.7087. Min Act: -0.0000

Data Index: 305743 (C4 (Web Text))

Max Activating Token Index: 786

Text #5

Max Range: 0.9095. Min Range: -0.9095

Max Act: 0.8595. Min Act: -0.0000

Data Index: 349013 (C4 (Web Text))

Max Activating Token Index: 285

Text #6

Max Range: 0.9095. Min Range: -0.9095

Max Act: 0.7164. Min Act: -0.0001

Data Index: 620544 (C4 (Web Text))

Max Activating Token Index: 864

Text #7

Max Range: 0.9095. Min Range: -0.9095

Max Act: 0.5797. Min Act: -0.0001

Data Index: 177057 (C4 (Web Text))

Max Activating Token Index: 483

Text #8

Max Range: 0.9095. Min Range: -0.9095

Max Act: 0.6376. Min Act: -0.0000

Data Index: 610064 (C4 (Web Text))

Max Activating Token Index: 806

Text #9

Max Range: 0.9095. Min Range: -0.9095

Max Act: 0.6449. Min Act: -0.0000

Data Index: 313921 (C4 (Web Text))

Max Activating Token Index: 297

Text #10

Max Range: 0.9095. Min Range: -0.9095

Max Act: 0.5891. Min Act: -0.0000

Data Index: 190653 (C4 (Web Text))

Max Activating Token Index: 965

Text #11

Max Range: 0.9095. Min Range: -0.9095

Max Act: 0.5323. Min Act: -0.0000

Data Index: 1046034 (C4 (Web Text))

Max Activating Token Index: 157

Text #12

Max Range: 0.9095. Min Range: -0.9095

Max Act: 0.6256. Min Act: -0.0000

Data Index: 174095 (C4 (Web Text))

Max Activating Token Index: 723

Text #13

Max Range: 0.9095. Min Range: -0.9095

Max Act: 0.5986. Min Act: -0.0000

Data Index: 553228 (C4 (Web Text))

Max Activating Token Index: 307

Text #14

Max Range: 0.9095. Min Range: -0.9095

Max Act: 0.5843. Min Act: -0.0000

Data Index: 93890 (C4 (Web Text))

Max Activating Token Index: 318

Text #15

Max Range: 0.9095. Min Range: -0.9095

Max Act: 0.6246. Min Act: -0.0000

Data Index: 866590 (C4 (Web Text))

Max Activating Token Index: 139

Text #16

Max Range: 0.9095. Min Range: -0.9095

Max Act: 0.6076. Min Act: -0.0001

Data Index: 596355 (C4 (Web Text))

Max Activating Token Index: 247

Text #17

Max Range: 0.9095. Min Range: -0.9095

Max Act: 0.5483. Min Act: -0.0000

Data Index: 115924 (C4 (Web Text))

Max Activating Token Index: 263

Text #18

Max Range: 0.9095. Min Range: -0.9095

Max Act: 0.6143. Min Act: -0.0000

Data Index: 656748 (C4 (Web Text))

Max Activating Token Index: 169

Text #19

Max Range: 0.9095. Min Range: -0.9095

Max Act: 0.5174. Min Act: -0.0001

Data Index: 369320 (C4 (Web Text))

Max Activating Token Index: 564