Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1059 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1343. Min Range: -0.1343

Max Act: 0.1286. Min Act: -0.0002

Data Index: 475829 (C4 (Web Text))

Max Activating Token Index: 327

Text #1

Max Range: 0.1343. Min Range: -0.1343

Max Act: 0.1343. Min Act: -0.0001

Data Index: 13091 (C4 (Web Text))

Max Activating Token Index: 1008

Text #2

Max Range: 0.1343. Min Range: -0.1343

Max Act: 0.1181. Min Act: -0.0002

Data Index: 1310585 (C4 (Web Text))

Max Activating Token Index: 1001

Text #3

Max Range: 0.1343. Min Range: -0.1343

Max Act: 0.1216. Min Act: -0.0002

Data Index: 1027535 (C4 (Web Text))

Max Activating Token Index: 492

Text #4

Max Range: 0.1343. Min Range: -0.1343

Max Act: 0.1237. Min Act: -0.0002

Data Index: 410046 (C4 (Web Text))

Max Activating Token Index: 615

Text #5

Max Range: 0.1343. Min Range: -0.1343

Max Act: 0.1162. Min Act: -0.0002

Data Index: 738397 (C4 (Web Text))

Max Activating Token Index: 701

Text #6

Max Range: 0.1343. Min Range: -0.1343

Max Act: 0.1171. Min Act: -0.0001

Data Index: 1282115 (C4 (Web Text))

Max Activating Token Index: 733

Text #7

Max Range: 0.1343. Min Range: -0.1343

Max Act: 0.1147. Min Act: -0.0002

Data Index: 1352494 (C4 (Web Text))

Max Activating Token Index: 33

Text #8

Max Range: 0.1343. Min Range: -0.1343

Max Act: 0.1099. Min Act: -0.0002

Data Index: 1315180 (C4 (Web Text))

Max Activating Token Index: 825

Text #9

Max Range: 0.1343. Min Range: -0.1343

Max Act: 0.1145. Min Act: -0.0002

Data Index: 623436 (C4 (Web Text))

Max Activating Token Index: 210

Text #10

Max Range: 0.1343. Min Range: -0.1343

Max Act: 0.1123. Min Act: -0.0001

Data Index: 1109582 (C4 (Web Text))

Max Activating Token Index: 377

Text #11

Max Range: 0.1343. Min Range: -0.1343

Max Act: 0.1137. Min Act: -0.0002

Data Index: 213983 (C4 (Web Text))

Max Activating Token Index: 464

Text #12

Max Range: 0.1343. Min Range: -0.1343

Max Act: 0.1098. Min Act: -0.0001

Data Index: 61580 (C4 (Web Text))

Max Activating Token Index: 720

Text #13

Max Range: 0.1343. Min Range: -0.1343

Max Act: 0.1066. Min Act: -0.0002

Data Index: 816025 (C4 (Web Text))

Max Activating Token Index: 873

Text #14

Max Range: 0.1343. Min Range: -0.1343

Max Act: 0.1149. Min Act: -0.0001

Data Index: 1075865 (C4 (Web Text))

Max Activating Token Index: 386

Text #15

Max Range: 0.1343. Min Range: -0.1343

Max Act: 0.1108. Min Act: -0.0002

Data Index: 176259 (C4 (Web Text))

Max Activating Token Index: 17

Text #16

Max Range: 0.1343. Min Range: -0.1343

Max Act: 0.1118. Min Act: -0.0001

Data Index: 1233720 (C4 (Web Text))

Max Activating Token Index: 925

Text #17

Max Range: 0.1343. Min Range: -0.1343

Max Act: 0.1109. Min Act: -0.0002

Data Index: 947087 (C4 (Web Text))

Max Activating Token Index: 943

Text #18

Max Range: 0.1343. Min Range: -0.1343

Max Act: 0.1095. Min Act: -0.0002

Data Index: 190181 (C4 (Web Text))

Max Activating Token Index: 989

Text #19

Max Range: 0.1343. Min Range: -0.1343

Max Act: 0.1104. Min Act: -0.0002

Data Index: 1113823 (C4 (Web Text))

Max Activating Token Index: 593