Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2279 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2134. Min Range: -0.2134

Max Act: 0.2134. Min Act: -0.0001

Data Index: 1086521 (C4 (Web Text))

Max Activating Token Index: 278

Text #1

Max Range: 0.2134. Min Range: -0.2134

Max Act: 0.2108. Min Act: -0.0001

Data Index: 712485 (C4 (Web Text))

Max Activating Token Index: 407

Text #2

Max Range: 0.2134. Min Range: -0.2134

Max Act: 0.2127. Min Act: -0.0001

Data Index: 391216 (C4 (Web Text))

Max Activating Token Index: 896

Text #3

Max Range: 0.2134. Min Range: -0.2134

Max Act: 0.1912. Min Act: -0.0001

Data Index: 322927 (C4 (Web Text))

Max Activating Token Index: 572

Text #4

Max Range: 0.2134. Min Range: -0.2134

Max Act: 0.1959. Min Act: -0.0001

Data Index: 921155 (C4 (Web Text))

Max Activating Token Index: 744

Text #5

Max Range: 0.2134. Min Range: -0.2134

Max Act: 0.1956. Min Act: -0.0001

Data Index: 78315 (C4 (Web Text))

Max Activating Token Index: 427

Text #6

Max Range: 0.2134. Min Range: -0.2134

Max Act: 0.1827. Min Act: -0.0001

Data Index: 15986 (C4 (Web Text))

Max Activating Token Index: 867

Text #7

Max Range: 0.2134. Min Range: -0.2134

Max Act: 0.1970. Min Act: -0.0001

Data Index: 713250 (C4 (Web Text))

Max Activating Token Index: 69

Text #8

Max Range: 0.2134. Min Range: -0.2134

Max Act: 0.1879. Min Act: -0.0001

Data Index: 691783 (C4 (Web Text))

Max Activating Token Index: 168

Text #9

Max Range: 0.2134. Min Range: -0.2134

Max Act: 0.1861. Min Act: -0.0001

Data Index: 178241 (C4 (Web Text))

Max Activating Token Index: 773

Text #10

Max Range: 0.2134. Min Range: -0.2134

Max Act: 0.1809. Min Act: -0.0001

Data Index: 1021694 (C4 (Web Text))

Max Activating Token Index: 148

Text #11

Max Range: 0.2134. Min Range: -0.2134

Max Act: 0.1917. Min Act: -0.0001

Data Index: 1106914 (C4 (Web Text))

Max Activating Token Index: 949

Text #12

Max Range: 0.2134. Min Range: -0.2134

Max Act: 0.1790. Min Act: -0.0001

Data Index: 1153078 (C4 (Web Text))

Max Activating Token Index: 561

Text #13

Max Range: 0.2134. Min Range: -0.2134

Max Act: 0.1689. Min Act: -0.0001

Data Index: 468172 (C4 (Web Text))

Max Activating Token Index: 890

Text #14

Max Range: 0.2134. Min Range: -0.2134

Max Act: 0.1721. Min Act: -0.0001

Data Index: 121854 (C4 (Web Text))

Max Activating Token Index: 588

Text #15

Max Range: 0.2134. Min Range: -0.2134

Max Act: 0.1666. Min Act: -0.0001

Data Index: 320273 (C4 (Web Text))

Max Activating Token Index: 152

Text #16

Max Range: 0.2134. Min Range: -0.2134

Max Act: 0.1773. Min Act: -0.0001

Data Index: 440353 (C4 (Web Text))

Max Activating Token Index: 847

Text #17

Max Range: 0.2134. Min Range: -0.2134

Max Act: 0.1768. Min Act: -0.0001

Data Index: 1101958 (C4 (Web Text))

Max Activating Token Index: 650

Text #18

Max Range: 0.2134. Min Range: -0.2134

Max Act: 0.1754. Min Act: -0.0001

Data Index: 1163070 (C4 (Web Text))

Max Activating Token Index: 675

Text #19

Max Range: 0.2134. Min Range: -0.2134

Max Act: 0.1701. Min Act: -0.0001

Data Index: 571833 (C4 (Web Text))

Max Activating Token Index: 777