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

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

Neuron 3287 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7598. Min Range: -1.7598

Max Act: 1.7598. Min Act: -0.0000

Data Index: 177478 (C4 (Web Text))

Max Activating Token Index: 127

Text #1

Max Range: 1.7598. Min Range: -1.7598

Max Act: 1.6877. Min Act: -0.0000

Data Index: 1090907 (C4 (Web Text))

Max Activating Token Index: 913

Text #2

Max Range: 1.7598. Min Range: -1.7598

Max Act: 1.6646. Min Act: -0.0000

Data Index: 1124086 (C4 (Web Text))

Max Activating Token Index: 109

Text #3

Max Range: 1.7598. Min Range: -1.7598

Max Act: 1.5017. Min Act: -0.0000

Data Index: 927610 (C4 (Web Text))

Max Activating Token Index: 342

Text #4

Max Range: 1.7598. Min Range: -1.7598

Max Act: 1.4338. Min Act: -0.0000

Data Index: 58049 (C4 (Web Text))

Max Activating Token Index: 813

Text #5

Max Range: 1.7598. Min Range: -1.7598

Max Act: 1.5638. Min Act: -0.0000

Data Index: 419586 (C4 (Web Text))

Max Activating Token Index: 502

Text #6

Max Range: 1.7598. Min Range: -1.7598

Max Act: 1.4456. Min Act: -0.0000

Data Index: 1212580 (C4 (Web Text))

Max Activating Token Index: 589

Text #7

Max Range: 1.7598. Min Range: -1.7598

Max Act: 1.5452. Min Act: -0.0000

Data Index: 927933 (C4 (Web Text))

Max Activating Token Index: 338

Text #8

Max Range: 1.7598. Min Range: -1.7598

Max Act: 1.5118. Min Act: -0.0000

Data Index: 621545 (C4 (Web Text))

Max Activating Token Index: 307

Text #9

Max Range: 1.7598. Min Range: -1.7598

Max Act: 1.3076. Min Act: -0.0000

Data Index: 349105 (C4 (Web Text))

Max Activating Token Index: 725

Text #10

Max Range: 1.7598. Min Range: -1.7598

Max Act: 1.3851. Min Act: -0.0000

Data Index: 1650829 (Python Code)

Max Activating Token Index: 446

Text #11

Max Range: 1.7598. Min Range: -1.7598

Max Act: 1.3367. Min Act: -0.0000

Data Index: 570819 (C4 (Web Text))

Max Activating Token Index: 842

Text #12

Max Range: 1.7598. Min Range: -1.7598

Max Act: 1.3048. Min Act: -0.0000

Data Index: 1146329 (C4 (Web Text))

Max Activating Token Index: 415

Text #13

Max Range: 1.7598. Min Range: -1.7598

Max Act: 1.2806. Min Act: -0.0000

Data Index: 925696 (C4 (Web Text))

Max Activating Token Index: 413

Text #14

Max Range: 1.7598. Min Range: -1.7598

Max Act: 1.2880. Min Act: -0.0000

Data Index: 249757 (C4 (Web Text))

Max Activating Token Index: 518

Text #15

Max Range: 1.7598. Min Range: -1.7598

Max Act: 1.2038. Min Act: -0.0000

Data Index: 774730 (C4 (Web Text))

Max Activating Token Index: 148

Text #16

Max Range: 1.7598. Min Range: -1.7598

Max Act: 1.2773. Min Act: -0.0000

Data Index: 1357985 (C4 (Web Text))

Max Activating Token Index: 872

Text #17

Max Range: 1.7598. Min Range: -1.7598

Max Act: 1.2348. Min Act: -0.0000

Data Index: 1579342 (Python Code)

Max Activating Token Index: 683

Text #18

Max Range: 1.7598. Min Range: -1.7598

Max Act: 1.2430. Min Act: -0.0000

Data Index: 1046291 (C4 (Web Text))

Max Activating Token Index: 673

Text #19

Max Range: 1.7598. Min Range: -1.7598

Max Act: 1.2151. Min Act: -0.0000

Data Index: 939344 (C4 (Web Text))

Max Activating Token Index: 325