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

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

Neuron 1333 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: 6.7184. Min Range: -6.7184

Max Act: 6.7184. Min Act: -0.0000

Data Index: 1165080 (C4 (Web Text))

Max Activating Token Index: 453

Text #1

Max Range: 6.7184. Min Range: -6.7184

Max Act: 6.3005. Min Act: -0.0000

Data Index: 39586 (C4 (Web Text))

Max Activating Token Index: 710

Text #2

Max Range: 6.7184. Min Range: -6.7184

Max Act: 5.8465. Min Act: -0.0000

Data Index: 48837 (C4 (Web Text))

Max Activating Token Index: 544

Text #3

Max Range: 6.7184. Min Range: -6.7184

Max Act: 6.0440. Min Act: -0.0000

Data Index: 564754 (C4 (Web Text))

Max Activating Token Index: 955

Text #4

Max Range: 6.7184. Min Range: -6.7184

Max Act: 6.0996. Min Act: -0.0000

Data Index: 1044162 (C4 (Web Text))

Max Activating Token Index: 762

Text #5

Max Range: 6.7184. Min Range: -6.7184

Max Act: 5.5185. Min Act: -0.0000

Data Index: 103287 (C4 (Web Text))

Max Activating Token Index: 248

Text #6

Max Range: 6.7184. Min Range: -6.7184

Max Act: 5.4630. Min Act: -0.0000

Data Index: 459359 (C4 (Web Text))

Max Activating Token Index: 287

Text #7

Max Range: 6.7184. Min Range: -6.7184

Max Act: 5.4310. Min Act: -0.0000

Data Index: 684781 (C4 (Web Text))

Max Activating Token Index: 202

Text #8

Max Range: 6.7184. Min Range: -6.7184

Max Act: 5.4272. Min Act: -0.0000

Data Index: 321416 (C4 (Web Text))

Max Activating Token Index: 26

Text #9

Max Range: 6.7184. Min Range: -6.7184

Max Act: 5.2921. Min Act: -0.0000

Data Index: 897780 (C4 (Web Text))

Max Activating Token Index: 776

Text #10

Max Range: 6.7184. Min Range: -6.7184

Max Act: 5.0963. Min Act: -0.0000

Data Index: 1081765 (C4 (Web Text))

Max Activating Token Index: 444

Text #11

Max Range: 6.7184. Min Range: -6.7184

Max Act: 5.0797. Min Act: -0.0000

Data Index: 1654752 (Python Code)

Max Activating Token Index: 263

Text #12

Max Range: 6.7184. Min Range: -6.7184

Max Act: 5.2517. Min Act: -0.0000

Data Index: 1234700 (C4 (Web Text))

Max Activating Token Index: 401

Text #13

Max Range: 6.7184. Min Range: -6.7184

Max Act: 5.1870. Min Act: -0.0000

Data Index: 119496 (C4 (Web Text))

Max Activating Token Index: 396

Text #14

Max Range: 6.7184. Min Range: -6.7184

Max Act: 5.1867. Min Act: -0.0000

Data Index: 263865 (C4 (Web Text))

Max Activating Token Index: 196

Text #15

Max Range: 6.7184. Min Range: -6.7184

Max Act: 5.1371. Min Act: -0.0000

Data Index: 237704 (C4 (Web Text))

Max Activating Token Index: 555

Text #16

Max Range: 6.7184. Min Range: -6.7184

Max Act: 5.0885. Min Act: -0.0000

Data Index: 1315927 (C4 (Web Text))

Max Activating Token Index: 1009

Text #17

Max Range: 6.7184. Min Range: -6.7184

Max Act: 5.0947. Min Act: -0.0000

Data Index: 253779 (C4 (Web Text))

Max Activating Token Index: 477

Text #18

Max Range: 6.7184. Min Range: -6.7184

Max Act: 4.8630. Min Act: -0.0000

Data Index: 600478 (C4 (Web Text))

Max Activating Token Index: 795

Text #19

Max Range: 6.7184. Min Range: -6.7184

Max Act: 5.0395. Min Act: -0.0000

Data Index: 1169766 (C4 (Web Text))

Max Activating Token Index: 122