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

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

Neuron 1302 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: 0.1410. Min Range: -0.1410

Max Act: 0.1410. Min Act: -0.0001

Data Index: 624265 (C4 (Web Text))

Max Activating Token Index: 143

Text #1

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1262. Min Act: -0.0002

Data Index: 65707 (C4 (Web Text))

Max Activating Token Index: 132

Text #2

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1251. Min Act: -0.0001

Data Index: 651540 (C4 (Web Text))

Max Activating Token Index: 854

Text #3

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1180. Min Act: -0.0002

Data Index: 1254143 (C4 (Web Text))

Max Activating Token Index: 357

Text #4

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1225. Min Act: -0.0002

Data Index: 563915 (C4 (Web Text))

Max Activating Token Index: 578

Text #5

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1173. Min Act: -0.0001

Data Index: 1161557 (C4 (Web Text))

Max Activating Token Index: 78

Text #6

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1129. Min Act: -0.0002

Data Index: 1019994 (C4 (Web Text))

Max Activating Token Index: 700

Text #7

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1156. Min Act: -0.0001

Data Index: 372216 (C4 (Web Text))

Max Activating Token Index: 8

Text #8

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1154. Min Act: -0.0002

Data Index: 942501 (C4 (Web Text))

Max Activating Token Index: 484

Text #9

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1152. Min Act: -0.0002

Data Index: 969595 (C4 (Web Text))

Max Activating Token Index: 405

Text #10

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1173. Min Act: -0.0002

Data Index: 846497 (C4 (Web Text))

Max Activating Token Index: 79

Text #11

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1141. Min Act: -0.0002

Data Index: 457452 (C4 (Web Text))

Max Activating Token Index: 108

Text #12

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1099. Min Act: -0.0002

Data Index: 1302046 (C4 (Web Text))

Max Activating Token Index: 7

Text #13

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1089. Min Act: -0.0001

Data Index: 1039895 (C4 (Web Text))

Max Activating Token Index: 269

Text #14

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1056. Min Act: -0.0002

Data Index: 464783 (C4 (Web Text))

Max Activating Token Index: 692

Text #15

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1082. Min Act: -0.0002

Data Index: 455147 (C4 (Web Text))

Max Activating Token Index: 999

Text #16

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1117. Min Act: -0.0002

Data Index: 558696 (C4 (Web Text))

Max Activating Token Index: 144

Text #17

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1059. Min Act: -0.0001

Data Index: 538892 (C4 (Web Text))

Max Activating Token Index: 895

Text #18

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1101. Min Act: -0.0002

Data Index: 190717 (C4 (Web Text))

Max Activating Token Index: 1003

Text #19

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1037. Min Act: -0.0002

Data Index: 313670 (C4 (Web Text))

Max Activating Token Index: 188