Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2695 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1380. Min Act: -0.0001

Data Index: 1469860 (Python Code)

Max Activating Token Index: 826

Text #1

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1387. Min Act: -0.0001

Data Index: 1623327 (Python Code)

Max Activating Token Index: 68

Text #2

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1410. Min Act: -0.0001

Data Index: 1456106 (Python Code)

Max Activating Token Index: 106

Text #3

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1298. Min Act: -0.0001

Data Index: 1301714 (C4 (Web Text))

Max Activating Token Index: 574

Text #4

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1230. Min Act: -0.0001

Data Index: 735077 (C4 (Web Text))

Max Activating Token Index: 21

Text #5

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1094. Min Act: -0.0001

Data Index: 1012617 (C4 (Web Text))

Max Activating Token Index: 286

Text #6

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1141. Min Act: -0.0001

Data Index: 737078 (C4 (Web Text))

Max Activating Token Index: 72

Text #7

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1231. Min Act: -0.0001

Data Index: 558376 (C4 (Web Text))

Max Activating Token Index: 568

Text #8

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1157. Min Act: -0.0001

Data Index: 1548997 (Python Code)

Max Activating Token Index: 726

Text #9

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1105. Min Act: -0.0001

Data Index: 1143461 (C4 (Web Text))

Max Activating Token Index: 703

Text #10

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.0911. Min Act: -0.0001

Data Index: 514744 (C4 (Web Text))

Max Activating Token Index: 782

Text #11

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1027. Min Act: -0.0001

Data Index: 103178 (C4 (Web Text))

Max Activating Token Index: 8

Text #12

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1054. Min Act: -0.0001

Data Index: 698016 (C4 (Web Text))

Max Activating Token Index: 98

Text #13

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1021. Min Act: -0.0001

Data Index: 1238203 (C4 (Web Text))

Max Activating Token Index: 874

Text #14

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1106. Min Act: -0.0001

Data Index: 29829 (C4 (Web Text))

Max Activating Token Index: 943

Text #15

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.0992. Min Act: -0.0002

Data Index: 313294 (C4 (Web Text))

Max Activating Token Index: 172

Text #16

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.0952. Min Act: -0.0001

Data Index: 1322269 (C4 (Web Text))

Max Activating Token Index: 525

Text #17

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.0893. Min Act: -0.0001

Data Index: 676254 (C4 (Web Text))

Max Activating Token Index: 700

Text #18

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.0948. Min Act: -0.0001

Data Index: 122034 (C4 (Web Text))

Max Activating Token Index: 519

Text #19

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1078. Min Act: -0.0001

Data Index: 942998 (C4 (Web Text))

Max Activating Token Index: 322