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

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

Neuron 2831 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: 1.9288. Min Range: -1.9288

Max Act: 1.9288. Min Act: -0.0000

Data Index: 1598040 (Python Code)

Max Activating Token Index: 959

Text #1

Max Range: 1.9288. Min Range: -1.9288

Max Act: 1.4818. Min Act: -0.0000

Data Index: 1592113 (Python Code)

Max Activating Token Index: 375

Text #2

Max Range: 1.9288. Min Range: -1.9288

Max Act: 1.5119. Min Act: -0.0000

Data Index: 1531902 (Python Code)

Max Activating Token Index: 510

Text #3

Max Range: 1.9288. Min Range: -1.9288

Max Act: 1.2536. Min Act: -0.0000

Data Index: 1558908 (Python Code)

Max Activating Token Index: 294

Text #4

Max Range: 1.9288. Min Range: -1.9288

Max Act: 1.3445. Min Act: -0.0000

Data Index: 748840 (C4 (Web Text))

Max Activating Token Index: 1011

Text #5

Max Range: 1.9288. Min Range: -1.9288

Max Act: 1.4094. Min Act: -0.0000

Data Index: 1623539 (Python Code)

Max Activating Token Index: 736

Text #6

Max Range: 1.9288. Min Range: -1.9288

Max Act: 1.3059. Min Act: -0.0000

Data Index: 1371339 (Python Code)

Max Activating Token Index: 462

Text #7

Max Range: 1.9288. Min Range: -1.9288

Max Act: 1.3783. Min Act: -0.0000

Data Index: 433629 (C4 (Web Text))

Max Activating Token Index: 188

Text #8

Max Range: 1.9288. Min Range: -1.9288

Max Act: 1.3258. Min Act: -0.0000

Data Index: 79375 (C4 (Web Text))

Max Activating Token Index: 814

Text #9

Max Range: 1.9288. Min Range: -1.9288

Max Act: 1.4007. Min Act: -0.0000

Data Index: 245452 (C4 (Web Text))

Max Activating Token Index: 628

Text #10

Max Range: 1.9288. Min Range: -1.9288

Max Act: 1.2577. Min Act: -0.0000

Data Index: 1648119 (Python Code)

Max Activating Token Index: 844

Text #11

Max Range: 1.9288. Min Range: -1.9288

Max Act: 1.4101. Min Act: -0.0000

Data Index: 4932 (C4 (Web Text))

Max Activating Token Index: 885

Text #12

Max Range: 1.9288. Min Range: -1.9288

Max Act: 1.3226. Min Act: -0.0000

Data Index: 824174 (C4 (Web Text))

Max Activating Token Index: 234

Text #13

Max Range: 1.9288. Min Range: -1.9288

Max Act: 1.3031. Min Act: -0.0000

Data Index: 702443 (C4 (Web Text))

Max Activating Token Index: 281

Text #14

Max Range: 1.9288. Min Range: -1.9288

Max Act: 1.3049. Min Act: -0.0000

Data Index: 870950 (C4 (Web Text))

Max Activating Token Index: 639

Text #15

Max Range: 1.9288. Min Range: -1.9288

Max Act: 1.2852. Min Act: -0.0000

Data Index: 687153 (C4 (Web Text))

Max Activating Token Index: 667

Text #16

Max Range: 1.9288. Min Range: -1.9288

Max Act: 1.2562. Min Act: -0.0000

Data Index: 1317801 (C4 (Web Text))

Max Activating Token Index: 601

Text #17

Max Range: 1.9288. Min Range: -1.9288

Max Act: 1.2960. Min Act: -0.0000

Data Index: 706797 (C4 (Web Text))

Max Activating Token Index: 683

Text #18

Max Range: 1.9288. Min Range: -1.9288

Max Act: 1.2902. Min Act: -0.0000

Data Index: 1020948 (C4 (Web Text))

Max Activating Token Index: 807

Text #19

Max Range: 1.9288. Min Range: -1.9288

Max Act: 1.2781. Min Act: -0.0000

Data Index: 1223464 (C4 (Web Text))

Max Activating Token Index: 810