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

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

Neuron 4712 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4591. Min Range: -2.4591

Max Act: 2.2623. Min Act: -0.0000

Data Index: 138063 (C4 (Web Text))

Max Activating Token Index: 1001

Text #1

Max Range: 2.4591. Min Range: -2.4591

Max Act: 2.3787. Min Act: -0.0000

Data Index: 680738 (C4 (Web Text))

Max Activating Token Index: 32

Text #2

Max Range: 2.4591. Min Range: -2.4591

Max Act: 2.4591. Min Act: -0.0000

Data Index: 1315209 (C4 (Web Text))

Max Activating Token Index: 459

Text #3

Max Range: 2.4591. Min Range: -2.4591

Max Act: 2.3019. Min Act: -0.0000

Data Index: 741496 (C4 (Web Text))

Max Activating Token Index: 492

Text #4

Max Range: 2.4591. Min Range: -2.4591

Max Act: 2.2618. Min Act: -0.0000

Data Index: 47591 (C4 (Web Text))

Max Activating Token Index: 413

Text #5

Max Range: 2.4591. Min Range: -2.4591

Max Act: 2.2312. Min Act: -0.0000

Data Index: 1010691 (C4 (Web Text))

Max Activating Token Index: 617

Text #6

Max Range: 2.4591. Min Range: -2.4591

Max Act: 2.0153. Min Act: -0.0000

Data Index: 233972 (C4 (Web Text))

Max Activating Token Index: 883

Text #7

Max Range: 2.4591. Min Range: -2.4591

Max Act: 2.0762. Min Act: -0.0000

Data Index: 1273027 (C4 (Web Text))

Max Activating Token Index: 754

Text #8

Max Range: 2.4591. Min Range: -2.4591

Max Act: 2.1847. Min Act: -0.0000

Data Index: 295068 (C4 (Web Text))

Max Activating Token Index: 774

Text #9

Max Range: 2.4591. Min Range: -2.4591

Max Act: 2.1223. Min Act: -0.0000

Data Index: 1168075 (C4 (Web Text))

Max Activating Token Index: 887

Text #10

Max Range: 2.4591. Min Range: -2.4591

Max Act: 1.9796. Min Act: -0.0000

Data Index: 717688 (C4 (Web Text))

Max Activating Token Index: 249

Text #11

Max Range: 2.4591. Min Range: -2.4591

Max Act: 2.1551. Min Act: -0.0000

Data Index: 1598432 (Python Code)

Max Activating Token Index: 803

Text #12

Max Range: 2.4591. Min Range: -2.4591

Max Act: 1.9187. Min Act: -0.0000

Data Index: 382479 (C4 (Web Text))

Max Activating Token Index: 351

Text #13

Max Range: 2.4591. Min Range: -2.4591

Max Act: 1.8007. Min Act: -0.0000

Data Index: 1651826 (Python Code)

Max Activating Token Index: 476

Text #14

Max Range: 2.4591. Min Range: -2.4591

Max Act: 2.0133. Min Act: -0.0000

Data Index: 152965 (C4 (Web Text))

Max Activating Token Index: 16

Text #15

Max Range: 2.4591. Min Range: -2.4591

Max Act: 2.1051. Min Act: -0.0000

Data Index: 1650012 (Python Code)

Max Activating Token Index: 469

Text #16

Max Range: 2.4591. Min Range: -2.4591

Max Act: 2.1154. Min Act: -0.0000

Data Index: 1376150 (Python Code)

Max Activating Token Index: 718

Text #17

Max Range: 2.4591. Min Range: -2.4591

Max Act: 1.8620. Min Act: -0.0000

Data Index: 704879 (C4 (Web Text))

Max Activating Token Index: 659

Text #18

Max Range: 2.4591. Min Range: -2.4591

Max Act: 2.0580. Min Act: -0.0001

Data Index: 674541 (C4 (Web Text))

Max Activating Token Index: 120

Text #19

Max Range: 2.4591. Min Range: -2.4591

Max Act: 1.9360. Min Act: -0.0000

Data Index: 1022905 (C4 (Web Text))

Max Activating Token Index: 65