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

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

Neuron 5555 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8172. Min Range: -0.8172

Max Act: 0.8172. Min Act: 0.0001

Data Index: 380331 (C4 (Web Text))

Max Activating Token Index: 191

Text #1

Max Range: 0.8172. Min Range: -0.8172

Max Act: 0.6738. Min Act: -0.0000

Data Index: 1340703 (C4 (Web Text))

Max Activating Token Index: 378

Text #2

Max Range: 0.8172. Min Range: -0.8172

Max Act: 0.6558. Min Act: -0.0000

Data Index: 290159 (C4 (Web Text))

Max Activating Token Index: 111

Text #3

Max Range: 0.8172. Min Range: -0.8172

Max Act: 0.6562. Min Act: -0.0000

Data Index: 511051 (C4 (Web Text))

Max Activating Token Index: 806

Text #4

Max Range: 0.8172. Min Range: -0.8172

Max Act: 0.6392. Min Act: -0.0000

Data Index: 1179357 (C4 (Web Text))

Max Activating Token Index: 780

Text #5

Max Range: 0.8172. Min Range: -0.8172

Max Act: 0.6461. Min Act: -0.0000

Data Index: 989115 (C4 (Web Text))

Max Activating Token Index: 431

Text #6

Max Range: 0.8172. Min Range: -0.8172

Max Act: 0.5918. Min Act: -0.0000

Data Index: 1331331 (C4 (Web Text))

Max Activating Token Index: 694

Text #7

Max Range: 0.8172. Min Range: -0.8172

Max Act: 0.6058. Min Act: 0.0000

Data Index: 653415 (C4 (Web Text))

Max Activating Token Index: 107

Text #8

Max Range: 0.8172. Min Range: -0.8172

Max Act: 0.6303. Min Act: -0.0000

Data Index: 394700 (C4 (Web Text))

Max Activating Token Index: 332

Text #9

Max Range: 0.8172. Min Range: -0.8172

Max Act: 0.5848. Min Act: -0.0000

Data Index: 509112 (C4 (Web Text))

Max Activating Token Index: 952

Text #10

Max Range: 0.8172. Min Range: -0.8172

Max Act: 0.5817. Min Act: -0.0000

Data Index: 934355 (C4 (Web Text))

Max Activating Token Index: 9

Text #11

Max Range: 0.8172. Min Range: -0.8172

Max Act: 0.5664. Min Act: -0.0000

Data Index: 1636684 (Python Code)

Max Activating Token Index: 380

Text #12

Max Range: 0.8172. Min Range: -0.8172

Max Act: 0.5533. Min Act: -0.0000

Data Index: 376527 (C4 (Web Text))

Max Activating Token Index: 641

Text #13

Max Range: 0.8172. Min Range: -0.8172

Max Act: 0.5620. Min Act: -0.0000

Data Index: 173836 (C4 (Web Text))

Max Activating Token Index: 155

Text #14

Max Range: 0.8172. Min Range: -0.8172

Max Act: 0.5537. Min Act: -0.0000

Data Index: 1358464 (C4 (Web Text))

Max Activating Token Index: 480

Text #15

Max Range: 0.8172. Min Range: -0.8172

Max Act: 0.5619. Min Act: -0.0000

Data Index: 1079638 (C4 (Web Text))

Max Activating Token Index: 797

Text #16

Max Range: 0.8172. Min Range: -0.8172

Max Act: 0.5316. Min Act: -0.0000

Data Index: 1084381 (C4 (Web Text))

Max Activating Token Index: 608

Text #17

Max Range: 0.8172. Min Range: -0.8172

Max Act: 0.5473. Min Act: -0.0000

Data Index: 1572830 (Python Code)

Max Activating Token Index: 319

Text #18

Max Range: 0.8172. Min Range: -0.8172

Max Act: 0.5186. Min Act: -0.0000

Data Index: 295444 (C4 (Web Text))

Max Activating Token Index: 868

Text #19

Max Range: 0.8172. Min Range: -0.8172

Max Act: 0.5210. Min Act: -0.0000

Data Index: 1026992 (C4 (Web Text))

Max Activating Token Index: 105