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

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

Neuron 4316 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: 1.6130. Min Range: -1.6130

Max Act: 1.6130. Min Act: -0.0000

Data Index: 856396 (C4 (Web Text))

Max Activating Token Index: 890

Text #1

Max Range: 1.6130. Min Range: -1.6130

Max Act: 1.2946. Min Act: -0.0000

Data Index: 542922 (C4 (Web Text))

Max Activating Token Index: 508

Text #2

Max Range: 1.6130. Min Range: -1.6130

Max Act: 1.3607. Min Act: -0.0000

Data Index: 1049282 (C4 (Web Text))

Max Activating Token Index: 820

Text #3

Max Range: 1.6130. Min Range: -1.6130

Max Act: 1.1805. Min Act: -0.0000

Data Index: 660642 (C4 (Web Text))

Max Activating Token Index: 663

Text #4

Max Range: 1.6130. Min Range: -1.6130

Max Act: 1.1478. Min Act: -0.0000

Data Index: 845796 (C4 (Web Text))

Max Activating Token Index: 1019

Text #5

Max Range: 1.6130. Min Range: -1.6130

Max Act: 1.1340. Min Act: -0.0000

Data Index: 293631 (C4 (Web Text))

Max Activating Token Index: 581

Text #6

Max Range: 1.6130. Min Range: -1.6130

Max Act: 1.1031. Min Act: -0.0000

Data Index: 624851 (C4 (Web Text))

Max Activating Token Index: 172

Text #7

Max Range: 1.6130. Min Range: -1.6130

Max Act: 1.0691. Min Act: -0.0000

Data Index: 1018939 (C4 (Web Text))

Max Activating Token Index: 360

Text #8

Max Range: 1.6130. Min Range: -1.6130

Max Act: 1.0003. Min Act: -0.0000

Data Index: 811770 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 1.6130. Min Range: -1.6130

Max Act: 1.0516. Min Act: -0.0000

Data Index: 905789 (C4 (Web Text))

Max Activating Token Index: 933

Text #10

Max Range: 1.6130. Min Range: -1.6130

Max Act: 1.1137. Min Act: -0.0000

Data Index: 260261 (C4 (Web Text))

Max Activating Token Index: 847

Text #11

Max Range: 1.6130. Min Range: -1.6130

Max Act: 1.0345. Min Act: -0.0000

Data Index: 704757 (C4 (Web Text))

Max Activating Token Index: 84

Text #12

Max Range: 1.6130. Min Range: -1.6130

Max Act: 1.0388. Min Act: -0.0000

Data Index: 650108 (C4 (Web Text))

Max Activating Token Index: 867

Text #13

Max Range: 1.6130. Min Range: -1.6130

Max Act: 1.0272. Min Act: -0.0000

Data Index: 1268727 (C4 (Web Text))

Max Activating Token Index: 187

Text #14

Max Range: 1.6130. Min Range: -1.6130

Max Act: 1.0212. Min Act: -0.0000

Data Index: 897225 (C4 (Web Text))

Max Activating Token Index: 69

Text #15

Max Range: 1.6130. Min Range: -1.6130

Max Act: 0.9660. Min Act: -0.0000

Data Index: 303662 (C4 (Web Text))

Max Activating Token Index: 245

Text #16

Max Range: 1.6130. Min Range: -1.6130

Max Act: 1.0083. Min Act: -0.0000

Data Index: 169463 (C4 (Web Text))

Max Activating Token Index: 418

Text #17

Max Range: 1.6130. Min Range: -1.6130

Max Act: 0.9434. Min Act: -0.0000

Data Index: 433684 (C4 (Web Text))

Max Activating Token Index: 55

Text #18

Max Range: 1.6130. Min Range: -1.6130

Max Act: 0.9390. Min Act: -0.0000

Data Index: 1092626 (C4 (Web Text))

Max Activating Token Index: 573

Text #19

Max Range: 1.6130. Min Range: -1.6130

Max Act: 0.9357. Min Act: -0.0000

Data Index: 1353435 (C4 (Web Text))

Max Activating Token Index: 899