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

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

Neuron 4661 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: 2.4078. Min Range: -2.4078

Max Act: 2.4078. Min Act: -0.0000

Data Index: 489690 (C4 (Web Text))

Max Activating Token Index: 54

Text #1

Max Range: 2.4078. Min Range: -2.4078

Max Act: 2.2244. Min Act: -0.0000

Data Index: 361583 (C4 (Web Text))

Max Activating Token Index: 305

Text #2

Max Range: 2.4078. Min Range: -2.4078

Max Act: 2.1077. Min Act: -0.0000

Data Index: 1018290 (C4 (Web Text))

Max Activating Token Index: 792

Text #3

Max Range: 2.4078. Min Range: -2.4078

Max Act: 2.3391. Min Act: -0.0000

Data Index: 321720 (C4 (Web Text))

Max Activating Token Index: 177

Text #4

Max Range: 2.4078. Min Range: -2.4078

Max Act: 2.3199. Min Act: -0.0000

Data Index: 723482 (C4 (Web Text))

Max Activating Token Index: 132

Text #5

Max Range: 2.4078. Min Range: -2.4078

Max Act: 2.0437. Min Act: -0.0000

Data Index: 510784 (C4 (Web Text))

Max Activating Token Index: 508

Text #6

Max Range: 2.4078. Min Range: -2.4078

Max Act: 2.1351. Min Act: -0.0000

Data Index: 857021 (C4 (Web Text))

Max Activating Token Index: 527

Text #7

Max Range: 2.4078. Min Range: -2.4078

Max Act: 1.9112. Min Act: -0.0000

Data Index: 962733 (C4 (Web Text))

Max Activating Token Index: 588

Text #8

Max Range: 2.4078. Min Range: -2.4078

Max Act: 2.0173. Min Act: -0.0000

Data Index: 175696 (C4 (Web Text))

Max Activating Token Index: 848

Text #9

Max Range: 2.4078. Min Range: -2.4078

Max Act: 2.1264. Min Act: -0.0000

Data Index: 556579 (C4 (Web Text))

Max Activating Token Index: 545

Text #10

Max Range: 2.4078. Min Range: -2.4078

Max Act: 2.0115. Min Act: -0.0000

Data Index: 1035713 (C4 (Web Text))

Max Activating Token Index: 247

Text #11

Max Range: 2.4078. Min Range: -2.4078

Max Act: 1.9935. Min Act: -0.0000

Data Index: 199552 (C4 (Web Text))

Max Activating Token Index: 160

Text #12

Max Range: 2.4078. Min Range: -2.4078

Max Act: 1.9807. Min Act: -0.0000

Data Index: 1021527 (C4 (Web Text))

Max Activating Token Index: 706

Text #13

Max Range: 2.4078. Min Range: -2.4078

Max Act: 2.1825. Min Act: -0.0000

Data Index: 220733 (C4 (Web Text))

Max Activating Token Index: 158

Text #14

Max Range: 2.4078. Min Range: -2.4078

Max Act: 1.8434. Min Act: -0.0000

Data Index: 642258 (C4 (Web Text))

Max Activating Token Index: 274

Text #15

Max Range: 2.4078. Min Range: -2.4078

Max Act: 2.0586. Min Act: -0.0000

Data Index: 556724 (C4 (Web Text))

Max Activating Token Index: 441

Text #16

Max Range: 2.4078. Min Range: -2.4078

Max Act: 1.9571. Min Act: -0.0000

Data Index: 968451 (C4 (Web Text))

Max Activating Token Index: 690

Text #17

Max Range: 2.4078. Min Range: -2.4078

Max Act: 1.9459. Min Act: -0.0000

Data Index: 744485 (C4 (Web Text))

Max Activating Token Index: 620

Text #18

Max Range: 2.4078. Min Range: -2.4078

Max Act: 2.1827. Min Act: -0.0000

Data Index: 809959 (C4 (Web Text))

Max Activating Token Index: 263

Text #19

Max Range: 2.4078. Min Range: -2.4078

Max Act: 2.0557. Min Act: -0.0000

Data Index: 1205391 (C4 (Web Text))

Max Activating Token Index: 76