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

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

Neuron 2725 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.8714. Min Range: -5.8714

Max Act: 5.8714. Min Act: -0.0000

Data Index: 1195937 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 5.8714. Min Range: -5.8714

Max Act: 5.3562. Min Act: -0.0000

Data Index: 185551 (C4 (Web Text))

Max Activating Token Index: 688

Text #2

Max Range: 5.8714. Min Range: -5.8714

Max Act: 5.5676. Min Act: -0.0000

Data Index: 100798 (C4 (Web Text))

Max Activating Token Index: 629

Text #3

Max Range: 5.8714. Min Range: -5.8714

Max Act: 5.3515. Min Act: -0.0000

Data Index: 631631 (C4 (Web Text))

Max Activating Token Index: 448

Text #4

Max Range: 5.8714. Min Range: -5.8714

Max Act: 5.2291. Min Act: -0.0000

Data Index: 861149 (C4 (Web Text))

Max Activating Token Index: 960

Text #5

Max Range: 5.8714. Min Range: -5.8714

Max Act: 5.3569. Min Act: -0.0000

Data Index: 694304 (C4 (Web Text))

Max Activating Token Index: 969

Text #6

Max Range: 5.8714. Min Range: -5.8714

Max Act: 5.1467. Min Act: -0.0000

Data Index: 371932 (C4 (Web Text))

Max Activating Token Index: 992

Text #7

Max Range: 5.8714. Min Range: -5.8714

Max Act: 5.0434. Min Act: -0.0000

Data Index: 963424 (C4 (Web Text))

Max Activating Token Index: 437

Text #8

Max Range: 5.8714. Min Range: -5.8714

Max Act: 4.6549. Min Act: -0.0000

Data Index: 1239700 (C4 (Web Text))

Max Activating Token Index: 314

Text #9

Max Range: 5.8714. Min Range: -5.8714

Max Act: 4.5460. Min Act: -0.0000

Data Index: 724811 (C4 (Web Text))

Max Activating Token Index: 182

Text #10

Max Range: 5.8714. Min Range: -5.8714

Max Act: 4.6556. Min Act: -0.0000

Data Index: 340203 (C4 (Web Text))

Max Activating Token Index: 133

Text #11

Max Range: 5.8714. Min Range: -5.8714

Max Act: 4.4280. Min Act: -0.0000

Data Index: 913222 (C4 (Web Text))

Max Activating Token Index: 814

Text #12

Max Range: 5.8714. Min Range: -5.8714

Max Act: 4.5541. Min Act: -0.0000

Data Index: 1424181 (Python Code)

Max Activating Token Index: 798

Text #13

Max Range: 5.8714. Min Range: -5.8714

Max Act: 4.5415. Min Act: -0.0000

Data Index: 11090 (C4 (Web Text))

Max Activating Token Index: 512

Text #14

Max Range: 5.8714. Min Range: -5.8714

Max Act: 4.8628. Min Act: -0.0000

Data Index: 769318 (C4 (Web Text))

Max Activating Token Index: 654

Text #15

Max Range: 5.8714. Min Range: -5.8714

Max Act: 3.9818. Min Act: -0.0000

Data Index: 1586470 (Python Code)

Max Activating Token Index: 962

Text #16

Max Range: 5.8714. Min Range: -5.8714

Max Act: 4.0987. Min Act: -0.0000

Data Index: 540641 (C4 (Web Text))

Max Activating Token Index: 497

Text #17

Max Range: 5.8714. Min Range: -5.8714

Max Act: 4.0915. Min Act: -0.0000

Data Index: 327853 (C4 (Web Text))

Max Activating Token Index: 219

Text #18

Max Range: 5.8714. Min Range: -5.8714

Max Act: 4.1954. Min Act: -0.0000

Data Index: 1493733 (Python Code)

Max Activating Token Index: 873

Text #19

Max Range: 5.8714. Min Range: -5.8714

Max Act: 4.1620. Min Act: -0.0000

Data Index: 163646 (C4 (Web Text))

Max Activating Token Index: 14