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

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

Neuron 1872 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.8697. Min Range: -6.8697

Max Act: 6.8697. Min Act: -0.0001

Data Index: 170589 (C4 (Web Text))

Max Activating Token Index: 18

Text #1

Max Range: 6.8697. Min Range: -6.8697

Max Act: 6.2217. Min Act: -0.0000

Data Index: 1031362 (C4 (Web Text))

Max Activating Token Index: 574

Text #2

Max Range: 6.8697. Min Range: -6.8697

Max Act: 5.9328. Min Act: -0.0001

Data Index: 1183872 (C4 (Web Text))

Max Activating Token Index: 12

Text #3

Max Range: 6.8697. Min Range: -6.8697

Max Act: 6.4539. Min Act: -0.0001

Data Index: 762467 (C4 (Web Text))

Max Activating Token Index: 408

Text #4

Max Range: 6.8697. Min Range: -6.8697

Max Act: 5.1900. Min Act: -0.0000

Data Index: 190659 (C4 (Web Text))

Max Activating Token Index: 571

Text #5

Max Range: 6.8697. Min Range: -6.8697

Max Act: 5.3150. Min Act: -0.0000

Data Index: 290992 (C4 (Web Text))

Max Activating Token Index: 56

Text #6

Max Range: 6.8697. Min Range: -6.8697

Max Act: 5.3097. Min Act: -0.0001

Data Index: 387764 (C4 (Web Text))

Max Activating Token Index: 61

Text #7

Max Range: 6.8697. Min Range: -6.8697

Max Act: 4.7518. Min Act: -0.0000

Data Index: 935385 (C4 (Web Text))

Max Activating Token Index: 842

Text #8

Max Range: 6.8697. Min Range: -6.8697

Max Act: 5.4911. Min Act: -0.0000

Data Index: 716354 (C4 (Web Text))

Max Activating Token Index: 123

Text #9

Max Range: 6.8697. Min Range: -6.8697

Max Act: 4.8885. Min Act: -0.0001

Data Index: 825204 (C4 (Web Text))

Max Activating Token Index: 916

Text #10

Max Range: 6.8697. Min Range: -6.8697

Max Act: 5.5308. Min Act: -0.0000

Data Index: 54326 (C4 (Web Text))

Max Activating Token Index: 309

Text #11

Max Range: 6.8697. Min Range: -6.8697

Max Act: 4.9668. Min Act: -0.0000

Data Index: 443003 (C4 (Web Text))

Max Activating Token Index: 200

Text #12

Max Range: 6.8697. Min Range: -6.8697

Max Act: 4.6462. Min Act: -0.0001

Data Index: 1325874 (C4 (Web Text))

Max Activating Token Index: 752

Text #13

Max Range: 6.8697. Min Range: -6.8697

Max Act: 5.1203. Min Act: -0.0000

Data Index: 588654 (C4 (Web Text))

Max Activating Token Index: 382

Text #14

Max Range: 6.8697. Min Range: -6.8697

Max Act: 5.0757. Min Act: -0.0000

Data Index: 501107 (C4 (Web Text))

Max Activating Token Index: 244

Text #15

Max Range: 6.8697. Min Range: -6.8697

Max Act: 4.6561. Min Act: -0.0000

Data Index: 1024996 (C4 (Web Text))

Max Activating Token Index: 408

Text #16

Max Range: 6.8697. Min Range: -6.8697

Max Act: 4.7830. Min Act: -0.0001

Data Index: 1003699 (C4 (Web Text))

Max Activating Token Index: 113

Text #17

Max Range: 6.8697. Min Range: -6.8697

Max Act: 4.9210. Min Act: -0.0001

Data Index: 43791 (C4 (Web Text))

Max Activating Token Index: 928

Text #18

Max Range: 6.8697. Min Range: -6.8697

Max Act: 4.4197. Min Act: -0.0000

Data Index: 614308 (C4 (Web Text))

Max Activating Token Index: 421

Text #19

Max Range: 6.8697. Min Range: -6.8697

Max Act: 4.3205. Min Act: -0.0000

Data Index: 303607 (C4 (Web Text))

Max Activating Token Index: 734