Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3395 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3150. Min Range: -0.3150

Max Act: 0.3150. Min Act: -0.0000

Data Index: 489343 (C4 (Web Text))

Max Activating Token Index: 977

Text #1

Max Range: 0.3150. Min Range: -0.3150

Max Act: 0.2353. Min Act: -0.0000

Data Index: 1166928 (C4 (Web Text))

Max Activating Token Index: 41

Text #2

Max Range: 0.3150. Min Range: -0.3150

Max Act: 0.2297. Min Act: -0.0000

Data Index: 1208873 (C4 (Web Text))

Max Activating Token Index: 785

Text #3

Max Range: 0.3150. Min Range: -0.3150

Max Act: 0.2220. Min Act: -0.0000

Data Index: 61154 (C4 (Web Text))

Max Activating Token Index: 394

Text #4

Max Range: 0.3150. Min Range: -0.3150

Max Act: 0.2000. Min Act: -0.0001

Data Index: 1289238 (C4 (Web Text))

Max Activating Token Index: 980

Text #5

Max Range: 0.3150. Min Range: -0.3150

Max Act: 0.2053. Min Act: -0.0001

Data Index: 518482 (C4 (Web Text))

Max Activating Token Index: 607

Text #6

Max Range: 0.3150. Min Range: -0.3150

Max Act: 0.2098. Min Act: -0.0001

Data Index: 343941 (C4 (Web Text))

Max Activating Token Index: 648

Text #7

Max Range: 0.3150. Min Range: -0.3150

Max Act: 0.1939. Min Act: -0.0001

Data Index: 33927 (C4 (Web Text))

Max Activating Token Index: 856

Text #8

Max Range: 0.3150. Min Range: -0.3150

Max Act: 0.1986. Min Act: -0.0001

Data Index: 427108 (C4 (Web Text))

Max Activating Token Index: 561

Text #9

Max Range: 0.3150. Min Range: -0.3150

Max Act: 0.1887. Min Act: -0.0001

Data Index: 200680 (C4 (Web Text))

Max Activating Token Index: 367

Text #10

Max Range: 0.3150. Min Range: -0.3150

Max Act: 0.1945. Min Act: -0.0000

Data Index: 1115346 (C4 (Web Text))

Max Activating Token Index: 957

Text #11

Max Range: 0.3150. Min Range: -0.3150

Max Act: 0.1870. Min Act: -0.0000

Data Index: 1111210 (C4 (Web Text))

Max Activating Token Index: 949

Text #12

Max Range: 0.3150. Min Range: -0.3150

Max Act: 0.1929. Min Act: -0.0000

Data Index: 780738 (C4 (Web Text))

Max Activating Token Index: 987

Text #13

Max Range: 0.3150. Min Range: -0.3150

Max Act: 0.1866. Min Act: -0.0000

Data Index: 1232211 (C4 (Web Text))

Max Activating Token Index: 797

Text #14

Max Range: 0.3150. Min Range: -0.3150

Max Act: 0.1866. Min Act: -0.0001

Data Index: 131976 (C4 (Web Text))

Max Activating Token Index: 165

Text #15

Max Range: 0.3150. Min Range: -0.3150

Max Act: 0.1919. Min Act: -0.0000

Data Index: 782205 (C4 (Web Text))

Max Activating Token Index: 603

Text #16

Max Range: 0.3150. Min Range: -0.3150

Max Act: 0.1981. Min Act: -0.0000

Data Index: 594715 (C4 (Web Text))

Max Activating Token Index: 515

Text #17

Max Range: 0.3150. Min Range: -0.3150

Max Act: 0.1899. Min Act: -0.0001

Data Index: 682187 (C4 (Web Text))

Max Activating Token Index: 504

Text #18

Max Range: 0.3150. Min Range: -0.3150

Max Act: 0.1823. Min Act: -0.0001

Data Index: 715823 (C4 (Web Text))

Max Activating Token Index: 177

Text #19

Max Range: 0.3150. Min Range: -0.3150

Max Act: 0.1852. Min Act: -0.0001

Data Index: 1031983 (C4 (Web Text))

Max Activating Token Index: 126