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

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

Neuron 3747 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: 0.2766. Min Range: -0.2766

Max Act: 0.2766. Min Act: -0.0000

Data Index: 173624 (C4 (Web Text))

Max Activating Token Index: 349

Text #1

Max Range: 0.2766. Min Range: -0.2766

Max Act: 0.2505. Min Act: -0.0000

Data Index: 1204197 (C4 (Web Text))

Max Activating Token Index: 777

Text #2

Max Range: 0.2766. Min Range: -0.2766

Max Act: 0.2685. Min Act: -0.0000

Data Index: 1321090 (C4 (Web Text))

Max Activating Token Index: 687

Text #3

Max Range: 0.2766. Min Range: -0.2766

Max Act: 0.2469. Min Act: -0.0000

Data Index: 608240 (C4 (Web Text))

Max Activating Token Index: 732

Text #4

Max Range: 0.2766. Min Range: -0.2766

Max Act: 0.2347. Min Act: -0.0000

Data Index: 290781 (C4 (Web Text))

Max Activating Token Index: 966

Text #5

Max Range: 0.2766. Min Range: -0.2766

Max Act: 0.2399. Min Act: -0.0000

Data Index: 449373 (C4 (Web Text))

Max Activating Token Index: 146

Text #6

Max Range: 0.2766. Min Range: -0.2766

Max Act: 0.2241. Min Act: -0.0000

Data Index: 150292 (C4 (Web Text))

Max Activating Token Index: 680

Text #7

Max Range: 0.2766. Min Range: -0.2766

Max Act: 0.2107. Min Act: -0.0000

Data Index: 607594 (C4 (Web Text))

Max Activating Token Index: 470

Text #8

Max Range: 0.2766. Min Range: -0.2766

Max Act: 0.2019. Min Act: -0.0000

Data Index: 967743 (C4 (Web Text))

Max Activating Token Index: 1003

Text #9

Max Range: 0.2766. Min Range: -0.2766

Max Act: 0.1905. Min Act: -0.0000

Data Index: 257027 (C4 (Web Text))

Max Activating Token Index: 267

Text #10

Max Range: 0.2766. Min Range: -0.2766

Max Act: 0.2045. Min Act: -0.0000

Data Index: 397881 (C4 (Web Text))

Max Activating Token Index: 1010

Text #11

Max Range: 0.2766. Min Range: -0.2766

Max Act: 0.1944. Min Act: -0.0000

Data Index: 445794 (C4 (Web Text))

Max Activating Token Index: 729

Text #12

Max Range: 0.2766. Min Range: -0.2766

Max Act: 0.1973. Min Act: -0.0000

Data Index: 610797 (C4 (Web Text))

Max Activating Token Index: 687

Text #13

Max Range: 0.2766. Min Range: -0.2766

Max Act: 0.2045. Min Act: -0.0000

Data Index: 999722 (C4 (Web Text))

Max Activating Token Index: 378

Text #14

Max Range: 0.2766. Min Range: -0.2766

Max Act: 0.1914. Min Act: -0.0000

Data Index: 1015954 (C4 (Web Text))

Max Activating Token Index: 685

Text #15

Max Range: 0.2766. Min Range: -0.2766

Max Act: 0.1911. Min Act: -0.0000

Data Index: 847462 (C4 (Web Text))

Max Activating Token Index: 355

Text #16

Max Range: 0.2766. Min Range: -0.2766

Max Act: 0.1962. Min Act: -0.0000

Data Index: 169798 (C4 (Web Text))

Max Activating Token Index: 161

Text #17

Max Range: 0.2766. Min Range: -0.2766

Max Act: 0.1892. Min Act: -0.0000

Data Index: 998019 (C4 (Web Text))

Max Activating Token Index: 609

Text #18

Max Range: 0.2766. Min Range: -0.2766

Max Act: 0.1928. Min Act: -0.0000

Data Index: 170603 (C4 (Web Text))

Max Activating Token Index: 956

Text #19

Max Range: 0.2766. Min Range: -0.2766

Max Act: 0.1858. Min Act: -0.0000

Data Index: 486335 (C4 (Web Text))

Max Activating Token Index: 10