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

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

Neuron 710 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: 0.1271. Min Range: -0.1271

Max Act: 0.1217. Min Act: -0.0002

Data Index: 1487467 (Python Code)

Max Activating Token Index: 477

Text #1

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.1271. Min Act: -0.0002

Data Index: 1451042 (Python Code)

Max Activating Token Index: 988

Text #2

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.1213. Min Act: -0.0002

Data Index: 1551570 (Python Code)

Max Activating Token Index: 706

Text #3

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.1164. Min Act: -0.0002

Data Index: 1529610 (Python Code)

Max Activating Token Index: 956

Text #4

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.1122. Min Act: -0.0002

Data Index: 1463522 (Python Code)

Max Activating Token Index: 898

Text #5

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.1113. Min Act: -0.0002

Data Index: 1648519 (Python Code)

Max Activating Token Index: 173

Text #6

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.1189. Min Act: -0.0002

Data Index: 1547846 (Python Code)

Max Activating Token Index: 592

Text #7

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.1035. Min Act: -0.0002

Data Index: 1385099 (Python Code)

Max Activating Token Index: 627

Text #8

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.1105. Min Act: -0.0002

Data Index: 1392814 (Python Code)

Max Activating Token Index: 774

Text #9

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.1091. Min Act: -0.0002

Data Index: 1509339 (Python Code)

Max Activating Token Index: 342

Text #10

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.1093. Min Act: -0.0002

Data Index: 1429937 (Python Code)

Max Activating Token Index: 200

Text #11

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.1085. Min Act: -0.0002

Data Index: 1439873 (Python Code)

Max Activating Token Index: 922

Text #12

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.1056. Min Act: -0.0002

Data Index: 1397877 (Python Code)

Max Activating Token Index: 563

Text #13

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.1023. Min Act: -0.0002

Data Index: 1539862 (Python Code)

Max Activating Token Index: 843

Text #14

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.1004. Min Act: -0.0002

Data Index: 1565244 (Python Code)

Max Activating Token Index: 848

Text #15

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.1010. Min Act: -0.0002

Data Index: 1427034 (Python Code)

Max Activating Token Index: 1019

Text #16

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.1047. Min Act: -0.0002

Data Index: 1369183 (Python Code)

Max Activating Token Index: 135

Text #17

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.1026. Min Act: -0.0002

Data Index: 1476399 (Python Code)

Max Activating Token Index: 928

Text #18

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.1054. Min Act: -0.0002

Data Index: 1492869 (Python Code)

Max Activating Token Index: 217

Text #19

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.1004. Min Act: -0.0002

Data Index: 1536669 (Python Code)

Max Activating Token Index: 352