Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1855 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.3971. Min Act: -0.0000

Data Index: 635928 (C4 (Web Text))

Max Activating Token Index: 218

Text #1

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.3492. Min Act: -0.0000

Data Index: 12465 (C4 (Web Text))

Max Activating Token Index: 829

Text #2

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.2989. Min Act: -0.0000

Data Index: 139604 (C4 (Web Text))

Max Activating Token Index: 924

Text #3

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.3032. Min Act: -0.0000

Data Index: 870829 (C4 (Web Text))

Max Activating Token Index: 759

Text #4

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.3097. Min Act: -0.0000

Data Index: 749464 (C4 (Web Text))

Max Activating Token Index: 986

Text #5

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.2869. Min Act: -0.0000

Data Index: 1635173 (Python Code)

Max Activating Token Index: 275

Text #6

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.2956. Min Act: -0.0000

Data Index: 442057 (C4 (Web Text))

Max Activating Token Index: 315

Text #7

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.2860. Min Act: -0.0000

Data Index: 731607 (C4 (Web Text))

Max Activating Token Index: 335

Text #8

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.2683. Min Act: -0.0000

Data Index: 827036 (C4 (Web Text))

Max Activating Token Index: 72

Text #9

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.2752. Min Act: -0.0000

Data Index: 713760 (C4 (Web Text))

Max Activating Token Index: 930

Text #10

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.3013. Min Act: -0.0000

Data Index: 316976 (C4 (Web Text))

Max Activating Token Index: 814

Text #11

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.2890. Min Act: -0.0000

Data Index: 421138 (C4 (Web Text))

Max Activating Token Index: 227

Text #12

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.2695. Min Act: -0.0000

Data Index: 310804 (C4 (Web Text))

Max Activating Token Index: 937

Text #13

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.2568. Min Act: -0.0000

Data Index: 1602440 (Python Code)

Max Activating Token Index: 290

Text #14

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.2727. Min Act: -0.0000

Data Index: 1060913 (C4 (Web Text))

Max Activating Token Index: 564

Text #15

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.2628. Min Act: -0.0000

Data Index: 152483 (C4 (Web Text))

Max Activating Token Index: 514

Text #16

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.2652. Min Act: -0.0000

Data Index: 1552093 (Python Code)

Max Activating Token Index: 948

Text #17

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.2728. Min Act: -0.0000

Data Index: 269194 (C4 (Web Text))

Max Activating Token Index: 852

Text #18

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.2618. Min Act: -0.0000

Data Index: 1080815 (C4 (Web Text))

Max Activating Token Index: 803

Text #19

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.2610. Min Act: -0.0000

Data Index: 994052 (C4 (Web Text))

Max Activating Token Index: 460