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

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

Neuron 4155 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3547. Min Range: -2.3547

Max Act: 2.3547. Min Act: -0.0000

Data Index: 991916 (C4 (Web Text))

Max Activating Token Index: 438

Text #1

Max Range: 2.3547. Min Range: -2.3547

Max Act: 2.0361. Min Act: -0.0000

Data Index: 270772 (C4 (Web Text))

Max Activating Token Index: 467

Text #2

Max Range: 2.3547. Min Range: -2.3547

Max Act: 2.0478. Min Act: -0.0000

Data Index: 716067 (C4 (Web Text))

Max Activating Token Index: 552

Text #3

Max Range: 2.3547. Min Range: -2.3547

Max Act: 2.0106. Min Act: -0.0000

Data Index: 1347495 (C4 (Web Text))

Max Activating Token Index: 1000

Text #4

Max Range: 2.3547. Min Range: -2.3547

Max Act: 2.0272. Min Act: -0.0000

Data Index: 566829 (C4 (Web Text))

Max Activating Token Index: 327

Text #5

Max Range: 2.3547. Min Range: -2.3547

Max Act: 2.0322. Min Act: -0.0000

Data Index: 1067321 (C4 (Web Text))

Max Activating Token Index: 41

Text #6

Max Range: 2.3547. Min Range: -2.3547

Max Act: 1.9942. Min Act: -0.0000

Data Index: 610335 (C4 (Web Text))

Max Activating Token Index: 457

Text #7

Max Range: 2.3547. Min Range: -2.3547

Max Act: 1.7476. Min Act: -0.0000

Data Index: 372682 (C4 (Web Text))

Max Activating Token Index: 975

Text #8

Max Range: 2.3547. Min Range: -2.3547

Max Act: 1.7795. Min Act: -0.0000

Data Index: 1198317 (C4 (Web Text))

Max Activating Token Index: 882

Text #9

Max Range: 2.3547. Min Range: -2.3547

Max Act: 1.7719. Min Act: -0.0000

Data Index: 515399 (C4 (Web Text))

Max Activating Token Index: 26

Text #10

Max Range: 2.3547. Min Range: -2.3547

Max Act: 1.8561. Min Act: -0.0000

Data Index: 352225 (C4 (Web Text))

Max Activating Token Index: 416

Text #11

Max Range: 2.3547. Min Range: -2.3547

Max Act: 1.5684. Min Act: -0.0000

Data Index: 1246653 (C4 (Web Text))

Max Activating Token Index: 151

Text #12

Max Range: 2.3547. Min Range: -2.3547

Max Act: 1.7599. Min Act: -0.0000

Data Index: 1067831 (C4 (Web Text))

Max Activating Token Index: 526

Text #13

Max Range: 2.3547. Min Range: -2.3547

Max Act: 1.7273. Min Act: -0.0000

Data Index: 769816 (C4 (Web Text))

Max Activating Token Index: 682

Text #14

Max Range: 2.3547. Min Range: -2.3547

Max Act: 1.6275. Min Act: -0.0000

Data Index: 1066434 (C4 (Web Text))

Max Activating Token Index: 859

Text #15

Max Range: 2.3547. Min Range: -2.3547

Max Act: 1.8220. Min Act: -0.0000

Data Index: 396513 (C4 (Web Text))

Max Activating Token Index: 990

Text #16

Max Range: 2.3547. Min Range: -2.3547

Max Act: 1.7033. Min Act: -0.0000

Data Index: 361702 (C4 (Web Text))

Max Activating Token Index: 422

Text #17

Max Range: 2.3547. Min Range: -2.3547

Max Act: 1.6929. Min Act: -0.0000

Data Index: 786895 (C4 (Web Text))

Max Activating Token Index: 685

Text #18

Max Range: 2.3547. Min Range: -2.3547

Max Act: 1.6843. Min Act: -0.0000

Data Index: 1159467 (C4 (Web Text))

Max Activating Token Index: 861

Text #19

Max Range: 2.3547. Min Range: -2.3547

Max Act: 1.6867. Min Act: -0.0000

Data Index: 418786 (C4 (Web Text))

Max Activating Token Index: 522