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

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

Neuron 2251 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: 5.2998. Min Range: -5.2998

Max Act: 5.2998. Min Act: -0.0000

Data Index: 904289 (C4 (Web Text))

Max Activating Token Index: 393

Text #1

Max Range: 5.2998. Min Range: -5.2998

Max Act: 4.5769. Min Act: -0.0000

Data Index: 452743 (C4 (Web Text))

Max Activating Token Index: 582

Text #2

Max Range: 5.2998. Min Range: -5.2998

Max Act: 3.9709. Min Act: -0.0000

Data Index: 745445 (C4 (Web Text))

Max Activating Token Index: 916

Text #3

Max Range: 5.2998. Min Range: -5.2998

Max Act: 4.0554. Min Act: -0.0000

Data Index: 144215 (C4 (Web Text))

Max Activating Token Index: 190

Text #4

Max Range: 5.2998. Min Range: -5.2998

Max Act: 4.7038. Min Act: -0.0000

Data Index: 678639 (C4 (Web Text))

Max Activating Token Index: 171

Text #5

Max Range: 5.2998. Min Range: -5.2998

Max Act: 3.5462. Min Act: -0.0000

Data Index: 304675 (C4 (Web Text))

Max Activating Token Index: 192

Text #6

Max Range: 5.2998. Min Range: -5.2998

Max Act: 3.8354. Min Act: -0.0000

Data Index: 592828 (C4 (Web Text))

Max Activating Token Index: 694

Text #7

Max Range: 5.2998. Min Range: -5.2998

Max Act: 3.9614. Min Act: -0.0000

Data Index: 400613 (C4 (Web Text))

Max Activating Token Index: 191

Text #8

Max Range: 5.2998. Min Range: -5.2998

Max Act: 3.5923. Min Act: -0.0000

Data Index: 463889 (C4 (Web Text))

Max Activating Token Index: 784

Text #9

Max Range: 5.2998. Min Range: -5.2998

Max Act: 3.5044. Min Act: -0.0000

Data Index: 854653 (C4 (Web Text))

Max Activating Token Index: 356

Text #10

Max Range: 5.2998. Min Range: -5.2998

Max Act: 3.4603. Min Act: -0.0000

Data Index: 255326 (C4 (Web Text))

Max Activating Token Index: 440

Text #11

Max Range: 5.2998. Min Range: -5.2998

Max Act: 3.0246. Min Act: -0.0000

Data Index: 313204 (C4 (Web Text))

Max Activating Token Index: 808

Text #12

Max Range: 5.2998. Min Range: -5.2998

Max Act: 2.9842. Min Act: -0.0000

Data Index: 609377 (C4 (Web Text))

Max Activating Token Index: 906

Text #13

Max Range: 5.2998. Min Range: -5.2998

Max Act: 3.0359. Min Act: -0.0000

Data Index: 927025 (C4 (Web Text))

Max Activating Token Index: 855

Text #14

Max Range: 5.2998. Min Range: -5.2998

Max Act: 3.1203. Min Act: -0.0000

Data Index: 656941 (C4 (Web Text))

Max Activating Token Index: 529

Text #15

Max Range: 5.2998. Min Range: -5.2998

Max Act: 3.0498. Min Act: -0.0000

Data Index: 502684 (C4 (Web Text))

Max Activating Token Index: 724

Text #16

Max Range: 5.2998. Min Range: -5.2998

Max Act: 2.8812. Min Act: -0.0000

Data Index: 1571200 (Python Code)

Max Activating Token Index: 900

Text #17

Max Range: 5.2998. Min Range: -5.2998

Max Act: 2.8093. Min Act: -0.0000

Data Index: 1287371 (C4 (Web Text))

Max Activating Token Index: 724

Text #18

Max Range: 5.2998. Min Range: -5.2998

Max Act: 3.0828. Min Act: -0.0000

Data Index: 1396967 (Python Code)

Max Activating Token Index: 284

Text #19

Max Range: 5.2998. Min Range: -5.2998

Max Act: 2.8782. Min Act: -0.0000

Data Index: 229714 (C4 (Web Text))

Max Activating Token Index: 331