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

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

Neuron 891 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5906. Min Range: -1.5906

Max Act: 1.5906. Min Act: -0.0000

Data Index: 1199837 (C4 (Web Text))

Max Activating Token Index: 203

Text #1

Max Range: 1.5906. Min Range: -1.5906

Max Act: 1.5753. Min Act: -0.0000

Data Index: 128909 (C4 (Web Text))

Max Activating Token Index: 1013

Text #2

Max Range: 1.5906. Min Range: -1.5906

Max Act: 1.4808. Min Act: -0.0000

Data Index: 397550 (C4 (Web Text))

Max Activating Token Index: 752

Text #3

Max Range: 1.5906. Min Range: -1.5906

Max Act: 1.5350. Min Act: -0.0000

Data Index: 362202 (C4 (Web Text))

Max Activating Token Index: 107

Text #4

Max Range: 1.5906. Min Range: -1.5906

Max Act: 1.2711. Min Act: -0.0000

Data Index: 951360 (C4 (Web Text))

Max Activating Token Index: 744

Text #5

Max Range: 1.5906. Min Range: -1.5906

Max Act: 1.3022. Min Act: -0.0000

Data Index: 184067 (C4 (Web Text))

Max Activating Token Index: 590

Text #6

Max Range: 1.5906. Min Range: -1.5906

Max Act: 1.1608. Min Act: -0.0000

Data Index: 333697 (C4 (Web Text))

Max Activating Token Index: 289

Text #7

Max Range: 1.5906. Min Range: -1.5906

Max Act: 1.3225. Min Act: -0.0000

Data Index: 762963 (C4 (Web Text))

Max Activating Token Index: 990

Text #8

Max Range: 1.5906. Min Range: -1.5906

Max Act: 1.2782. Min Act: -0.0000

Data Index: 490063 (C4 (Web Text))

Max Activating Token Index: 867

Text #9

Max Range: 1.5906. Min Range: -1.5906

Max Act: 1.2496. Min Act: -0.0000

Data Index: 314850 (C4 (Web Text))

Max Activating Token Index: 265

Text #10

Max Range: 1.5906. Min Range: -1.5906

Max Act: 1.1640. Min Act: -0.0000

Data Index: 230358 (C4 (Web Text))

Max Activating Token Index: 816

Text #11

Max Range: 1.5906. Min Range: -1.5906

Max Act: 1.1601. Min Act: -0.0000

Data Index: 998091 (C4 (Web Text))

Max Activating Token Index: 524

Text #12

Max Range: 1.5906. Min Range: -1.5906

Max Act: 1.1055. Min Act: -0.0000

Data Index: 707467 (C4 (Web Text))

Max Activating Token Index: 611

Text #13

Max Range: 1.5906. Min Range: -1.5906

Max Act: 1.1846. Min Act: -0.0000

Data Index: 179757 (C4 (Web Text))

Max Activating Token Index: 606

Text #14

Max Range: 1.5906. Min Range: -1.5906

Max Act: 1.0918. Min Act: -0.0000

Data Index: 154630 (C4 (Web Text))

Max Activating Token Index: 352

Text #15

Max Range: 1.5906. Min Range: -1.5906

Max Act: 1.3372. Min Act: -0.0000

Data Index: 1087689 (C4 (Web Text))

Max Activating Token Index: 847

Text #16

Max Range: 1.5906. Min Range: -1.5906

Max Act: 1.0994. Min Act: -0.0000

Data Index: 521069 (C4 (Web Text))

Max Activating Token Index: 94

Text #17

Max Range: 1.5906. Min Range: -1.5906

Max Act: 1.1005. Min Act: -0.0000

Data Index: 531014 (C4 (Web Text))

Max Activating Token Index: 144

Text #18

Max Range: 1.5906. Min Range: -1.5906

Max Act: 1.3388. Min Act: -0.0000

Data Index: 601330 (C4 (Web Text))

Max Activating Token Index: 817

Text #19

Max Range: 1.5906. Min Range: -1.5906

Max Act: 1.1023. Min Act: -0.0000

Data Index: 542190 (C4 (Web Text))

Max Activating Token Index: 559