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

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

Neuron 3438 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.1780. Min Range: -7.1780

Max Act: 7.1780. Min Act: -0.0000

Data Index: 339268 (C4 (Web Text))

Max Activating Token Index: 394

Text #1

Max Range: 7.1780. Min Range: -7.1780

Max Act: 6.3146. Min Act: -0.0000

Data Index: 438623 (C4 (Web Text))

Max Activating Token Index: 223

Text #2

Max Range: 7.1780. Min Range: -7.1780

Max Act: 5.7483. Min Act: -0.0000

Data Index: 510851 (C4 (Web Text))

Max Activating Token Index: 102

Text #3

Max Range: 7.1780. Min Range: -7.1780

Max Act: 5.7112. Min Act: -0.0000

Data Index: 377895 (C4 (Web Text))

Max Activating Token Index: 112

Text #4

Max Range: 7.1780. Min Range: -7.1780

Max Act: 5.4678. Min Act: -0.0000

Data Index: 128225 (C4 (Web Text))

Max Activating Token Index: 488

Text #5

Max Range: 7.1780. Min Range: -7.1780

Max Act: 5.5184. Min Act: -0.0000

Data Index: 1029511 (C4 (Web Text))

Max Activating Token Index: 299

Text #6

Max Range: 7.1780. Min Range: -7.1780

Max Act: 5.2454. Min Act: -0.0000

Data Index: 1175444 (C4 (Web Text))

Max Activating Token Index: 446

Text #7

Max Range: 7.1780. Min Range: -7.1780

Max Act: 5.1365. Min Act: -0.0000

Data Index: 680889 (C4 (Web Text))

Max Activating Token Index: 837

Text #8

Max Range: 7.1780. Min Range: -7.1780

Max Act: 4.8336. Min Act: -0.0000

Data Index: 502547 (C4 (Web Text))

Max Activating Token Index: 69

Text #9

Max Range: 7.1780. Min Range: -7.1780

Max Act: 4.8460. Min Act: -0.0000

Data Index: 1035460 (C4 (Web Text))

Max Activating Token Index: 432

Text #10

Max Range: 7.1780. Min Range: -7.1780

Max Act: 4.9837. Min Act: -0.0000

Data Index: 393826 (C4 (Web Text))

Max Activating Token Index: 424

Text #11

Max Range: 7.1780. Min Range: -7.1780

Max Act: 4.9331. Min Act: -0.0000

Data Index: 1128962 (C4 (Web Text))

Max Activating Token Index: 83

Text #12

Max Range: 7.1780. Min Range: -7.1780

Max Act: 4.7956. Min Act: -0.0000

Data Index: 594514 (C4 (Web Text))

Max Activating Token Index: 267

Text #13

Max Range: 7.1780. Min Range: -7.1780

Max Act: 4.6868. Min Act: -0.0000

Data Index: 265226 (C4 (Web Text))

Max Activating Token Index: 889

Text #14

Max Range: 7.1780. Min Range: -7.1780

Max Act: 4.6581. Min Act: -0.0000

Data Index: 989691 (C4 (Web Text))

Max Activating Token Index: 610

Text #15

Max Range: 7.1780. Min Range: -7.1780

Max Act: 4.6663. Min Act: -0.0000

Data Index: 631544 (C4 (Web Text))

Max Activating Token Index: 863

Text #16

Max Range: 7.1780. Min Range: -7.1780

Max Act: 4.6472. Min Act: -0.0000

Data Index: 1276048 (C4 (Web Text))

Max Activating Token Index: 739

Text #17

Max Range: 7.1780. Min Range: -7.1780

Max Act: 4.6032. Min Act: -0.0000

Data Index: 1101986 (C4 (Web Text))

Max Activating Token Index: 551

Text #18

Max Range: 7.1780. Min Range: -7.1780

Max Act: 4.6152. Min Act: -0.0000

Data Index: 108415 (C4 (Web Text))

Max Activating Token Index: 649

Text #19

Max Range: 7.1780. Min Range: -7.1780

Max Act: 4.1745. Min Act: -0.0000

Data Index: 1304324 (C4 (Web Text))

Max Activating Token Index: 416