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

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

Neuron 253 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: 0.6294. Min Range: -0.6294

Max Act: 0.6294. Min Act: -0.0000

Data Index: 53951 (C4 (Web Text))

Max Activating Token Index: 334

Text #1

Max Range: 0.6294. Min Range: -0.6294

Max Act: 0.5047. Min Act: -0.0000

Data Index: 626733 (C4 (Web Text))

Max Activating Token Index: 30

Text #2

Max Range: 0.6294. Min Range: -0.6294

Max Act: 0.4666. Min Act: -0.0000

Data Index: 514762 (C4 (Web Text))

Max Activating Token Index: 10

Text #3

Max Range: 0.6294. Min Range: -0.6294

Max Act: 0.4443. Min Act: -0.0000

Data Index: 394983 (C4 (Web Text))

Max Activating Token Index: 576

Text #4

Max Range: 0.6294. Min Range: -0.6294

Max Act: 0.4289. Min Act: -0.0000

Data Index: 228899 (C4 (Web Text))

Max Activating Token Index: 37

Text #5

Max Range: 0.6294. Min Range: -0.6294

Max Act: 0.3990. Min Act: -0.0000

Data Index: 1072898 (C4 (Web Text))

Max Activating Token Index: 891

Text #6

Max Range: 0.6294. Min Range: -0.6294

Max Act: 0.4059. Min Act: -0.0000

Data Index: 155095 (C4 (Web Text))

Max Activating Token Index: 906

Text #7

Max Range: 0.6294. Min Range: -0.6294

Max Act: 0.3727. Min Act: -0.0000

Data Index: 1075793 (C4 (Web Text))

Max Activating Token Index: 374

Text #8

Max Range: 0.6294. Min Range: -0.6294

Max Act: 0.4061. Min Act: -0.0000

Data Index: 761789 (C4 (Web Text))

Max Activating Token Index: 668

Text #9

Max Range: 0.6294. Min Range: -0.6294

Max Act: 0.3876. Min Act: -0.0000

Data Index: 2859 (C4 (Web Text))

Max Activating Token Index: 662

Text #10

Max Range: 0.6294. Min Range: -0.6294

Max Act: 0.4096. Min Act: -0.0000

Data Index: 537841 (C4 (Web Text))

Max Activating Token Index: 143

Text #11

Max Range: 0.6294. Min Range: -0.6294

Max Act: 0.4100. Min Act: -0.0000

Data Index: 694652 (C4 (Web Text))

Max Activating Token Index: 604

Text #12

Max Range: 0.6294. Min Range: -0.6294

Max Act: 0.4148. Min Act: 0.0000

Data Index: 676017 (C4 (Web Text))

Max Activating Token Index: 268

Text #13

Max Range: 0.6294. Min Range: -0.6294

Max Act: 0.3953. Min Act: -0.0000

Data Index: 1272510 (C4 (Web Text))

Max Activating Token Index: 785

Text #14

Max Range: 0.6294. Min Range: -0.6294

Max Act: 0.3869. Min Act: -0.0000

Data Index: 1221092 (C4 (Web Text))

Max Activating Token Index: 485

Text #15

Max Range: 0.6294. Min Range: -0.6294

Max Act: 0.3388. Min Act: -0.0000

Data Index: 1202456 (C4 (Web Text))

Max Activating Token Index: 109

Text #16

Max Range: 0.6294. Min Range: -0.6294

Max Act: 0.4124. Min Act: -0.0000

Data Index: 829438 (C4 (Web Text))

Max Activating Token Index: 868

Text #17

Max Range: 0.6294. Min Range: -0.6294

Max Act: 0.4198. Min Act: -0.0000

Data Index: 487257 (C4 (Web Text))

Max Activating Token Index: 909

Text #18

Max Range: 0.6294. Min Range: -0.6294

Max Act: 0.3998. Min Act: -0.0000

Data Index: 696150 (C4 (Web Text))

Max Activating Token Index: 351

Text #19

Max Range: 0.6294. Min Range: -0.6294

Max Act: 0.3497. Min Act: -0.0000

Data Index: 775558 (C4 (Web Text))

Max Activating Token Index: 274