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

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

Neuron 5296 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.2922. Min Range: -6.2922

Max Act: 6.2922. Min Act: -0.0000

Data Index: 1041855 (C4 (Web Text))

Max Activating Token Index: 770

Text #1

Max Range: 6.2922. Min Range: -6.2922

Max Act: 6.2019. Min Act: -0.0000

Data Index: 429997 (C4 (Web Text))

Max Activating Token Index: 1001

Text #2

Max Range: 6.2922. Min Range: -6.2922

Max Act: 5.9957. Min Act: -0.0000

Data Index: 442333 (C4 (Web Text))

Max Activating Token Index: 115

Text #3

Max Range: 6.2922. Min Range: -6.2922

Max Act: 5.9601. Min Act: -0.0000

Data Index: 476464 (C4 (Web Text))

Max Activating Token Index: 987

Text #4

Max Range: 6.2922. Min Range: -6.2922

Max Act: 5.9158. Min Act: -0.0000

Data Index: 1092202 (C4 (Web Text))

Max Activating Token Index: 199

Text #5

Max Range: 6.2922. Min Range: -6.2922

Max Act: 5.5912. Min Act: -0.0000

Data Index: 1108121 (C4 (Web Text))

Max Activating Token Index: 538

Text #6

Max Range: 6.2922. Min Range: -6.2922

Max Act: 5.5260. Min Act: -0.0000

Data Index: 290646 (C4 (Web Text))

Max Activating Token Index: 1015

Text #7

Max Range: 6.2922. Min Range: -6.2922

Max Act: 5.6296. Min Act: -0.0000

Data Index: 393761 (C4 (Web Text))

Max Activating Token Index: 445

Text #8

Max Range: 6.2922. Min Range: -6.2922

Max Act: 5.6060. Min Act: 0.0000

Data Index: 641832 (C4 (Web Text))

Max Activating Token Index: 94

Text #9

Max Range: 6.2922. Min Range: -6.2922

Max Act: 5.3526. Min Act: -0.0000

Data Index: 425470 (C4 (Web Text))

Max Activating Token Index: 522

Text #10

Max Range: 6.2922. Min Range: -6.2922

Max Act: 4.9871. Min Act: -0.0000

Data Index: 318924 (C4 (Web Text))

Max Activating Token Index: 344

Text #11

Max Range: 6.2922. Min Range: -6.2922

Max Act: 5.0715. Min Act: -0.0000

Data Index: 426717 (C4 (Web Text))

Max Activating Token Index: 481

Text #12

Max Range: 6.2922. Min Range: -6.2922

Max Act: 5.0153. Min Act: -0.0000

Data Index: 972094 (C4 (Web Text))

Max Activating Token Index: 787

Text #13

Max Range: 6.2922. Min Range: -6.2922

Max Act: 5.1614. Min Act: -0.0000

Data Index: 149373 (C4 (Web Text))

Max Activating Token Index: 64

Text #14

Max Range: 6.2922. Min Range: -6.2922

Max Act: 5.3155. Min Act: -0.0000

Data Index: 779045 (C4 (Web Text))

Max Activating Token Index: 101

Text #15

Max Range: 6.2922. Min Range: -6.2922

Max Act: 5.0913. Min Act: 0.0000

Data Index: 198069 (C4 (Web Text))

Max Activating Token Index: 949

Text #16

Max Range: 6.2922. Min Range: -6.2922

Max Act: 4.8974. Min Act: -0.0000

Data Index: 803779 (C4 (Web Text))

Max Activating Token Index: 315

Text #17

Max Range: 6.2922. Min Range: -6.2922

Max Act: 5.0768. Min Act: -0.0000

Data Index: 698356 (C4 (Web Text))

Max Activating Token Index: 33

Text #18

Max Range: 6.2922. Min Range: -6.2922

Max Act: 4.8362. Min Act: -0.0000

Data Index: 992667 (C4 (Web Text))

Max Activating Token Index: 720

Text #19

Max Range: 6.2922. Min Range: -6.2922

Max Act: 4.8102. Min Act: -0.0000

Data Index: 671295 (C4 (Web Text))

Max Activating Token Index: 165