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

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

Neuron 5256 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: 2.6509. Min Range: -2.6509

Max Act: 2.6509. Min Act: -0.0000

Data Index: 42372 (C4 (Web Text))

Max Activating Token Index: 629

Text #1

Max Range: 2.6509. Min Range: -2.6509

Max Act: 2.4043. Min Act: -0.0000

Data Index: 1300335 (C4 (Web Text))

Max Activating Token Index: 667

Text #2

Max Range: 2.6509. Min Range: -2.6509

Max Act: 2.4855. Min Act: -0.0000

Data Index: 735616 (C4 (Web Text))

Max Activating Token Index: 564

Text #3

Max Range: 2.6509. Min Range: -2.6509

Max Act: 2.4993. Min Act: -0.0000

Data Index: 278576 (C4 (Web Text))

Max Activating Token Index: 290

Text #4

Max Range: 2.6509. Min Range: -2.6509

Max Act: 1.9449. Min Act: -0.0000

Data Index: 404034 (C4 (Web Text))

Max Activating Token Index: 773

Text #5

Max Range: 2.6509. Min Range: -2.6509

Max Act: 2.1055. Min Act: -0.0000

Data Index: 928975 (C4 (Web Text))

Max Activating Token Index: 907

Text #6

Max Range: 2.6509. Min Range: -2.6509

Max Act: 2.1736. Min Act: -0.0000

Data Index: 790042 (C4 (Web Text))

Max Activating Token Index: 555

Text #7

Max Range: 2.6509. Min Range: -2.6509

Max Act: 2.1735. Min Act: -0.0000

Data Index: 142896 (C4 (Web Text))

Max Activating Token Index: 46

Text #8

Max Range: 2.6509. Min Range: -2.6509

Max Act: 2.1596. Min Act: -0.0000

Data Index: 931414 (C4 (Web Text))

Max Activating Token Index: 360

Text #9

Max Range: 2.6509. Min Range: -2.6509

Max Act: 2.1473. Min Act: -0.0000

Data Index: 667886 (C4 (Web Text))

Max Activating Token Index: 81

Text #10

Max Range: 2.6509. Min Range: -2.6509

Max Act: 2.1236. Min Act: -0.0000

Data Index: 1061553 (C4 (Web Text))

Max Activating Token Index: 763

Text #11

Max Range: 2.6509. Min Range: -2.6509

Max Act: 1.9944. Min Act: -0.0000

Data Index: 78056 (C4 (Web Text))

Max Activating Token Index: 352

Text #12

Max Range: 2.6509. Min Range: -2.6509

Max Act: 1.8151. Min Act: -0.0000

Data Index: 725330 (C4 (Web Text))

Max Activating Token Index: 421

Text #13

Max Range: 2.6509. Min Range: -2.6509

Max Act: 2.0037. Min Act: -0.0000

Data Index: 457893 (C4 (Web Text))

Max Activating Token Index: 530

Text #14

Max Range: 2.6509. Min Range: -2.6509

Max Act: 1.9778. Min Act: -0.0000

Data Index: 728667 (C4 (Web Text))

Max Activating Token Index: 279

Text #15

Max Range: 2.6509. Min Range: -2.6509

Max Act: 1.8225. Min Act: -0.0000

Data Index: 686214 (C4 (Web Text))

Max Activating Token Index: 973

Text #16

Max Range: 2.6509. Min Range: -2.6509

Max Act: 1.9065. Min Act: -0.0000

Data Index: 849055 (C4 (Web Text))

Max Activating Token Index: 134

Text #17

Max Range: 2.6509. Min Range: -2.6509

Max Act: 1.9016. Min Act: -0.0000

Data Index: 1171567 (C4 (Web Text))

Max Activating Token Index: 116

Text #18

Max Range: 2.6509. Min Range: -2.6509

Max Act: 1.8946. Min Act: -0.0000

Data Index: 537721 (C4 (Web Text))

Max Activating Token Index: 808

Text #19

Max Range: 2.6509. Min Range: -2.6509

Max Act: 1.7463. Min Act: -0.0000

Data Index: 402594 (C4 (Web Text))

Max Activating Token Index: 206