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

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

Neuron 1337 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: 0.1225. Min Range: -0.1225

Max Act: 0.1202. Min Act: -0.0001

Data Index: 502420 (C4 (Web Text))

Max Activating Token Index: 236

Text #1

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.1225. Min Act: -0.0001

Data Index: 40240 (C4 (Web Text))

Max Activating Token Index: 710

Text #2

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.1119. Min Act: -0.0001

Data Index: 243504 (C4 (Web Text))

Max Activating Token Index: 18

Text #3

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.1055. Min Act: -0.0001

Data Index: 238533 (C4 (Web Text))

Max Activating Token Index: 345

Text #4

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.1063. Min Act: -0.0001

Data Index: 299623 (C4 (Web Text))

Max Activating Token Index: 821

Text #5

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.0968. Min Act: -0.0001

Data Index: 102801 (C4 (Web Text))

Max Activating Token Index: 874

Text #6

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.1059. Min Act: -0.0001

Data Index: 728596 (C4 (Web Text))

Max Activating Token Index: 825

Text #7

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.1090. Min Act: -0.0001

Data Index: 779867 (C4 (Web Text))

Max Activating Token Index: 708

Text #8

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.1041. Min Act: -0.0001

Data Index: 807945 (C4 (Web Text))

Max Activating Token Index: 68

Text #9

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.1048. Min Act: -0.0001

Data Index: 1163109 (C4 (Web Text))

Max Activating Token Index: 33

Text #10

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.0990. Min Act: -0.0001

Data Index: 628279 (C4 (Web Text))

Max Activating Token Index: 1014

Text #11

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.1026. Min Act: -0.0001

Data Index: 251860 (C4 (Web Text))

Max Activating Token Index: 675

Text #12

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.0958. Min Act: -0.0001

Data Index: 204437 (C4 (Web Text))

Max Activating Token Index: 908

Text #13

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.0922. Min Act: -0.0001

Data Index: 719299 (C4 (Web Text))

Max Activating Token Index: 294

Text #14

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.1009. Min Act: -0.0001

Data Index: 1296444 (C4 (Web Text))

Max Activating Token Index: 82

Text #15

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.1003. Min Act: -0.0001

Data Index: 771354 (C4 (Web Text))

Max Activating Token Index: 932

Text #16

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.0987. Min Act: -0.0001

Data Index: 619754 (C4 (Web Text))

Max Activating Token Index: 429

Text #17

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.0946. Min Act: -0.0001

Data Index: 1309034 (C4 (Web Text))

Max Activating Token Index: 47

Text #18

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.0980. Min Act: -0.0001

Data Index: 909901 (C4 (Web Text))

Max Activating Token Index: 828

Text #19

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.1116. Min Act: -0.0001

Data Index: 964236 (C4 (Web Text))

Max Activating Token Index: 813