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

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

Neuron 4481 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1262. Min Range: -0.1262

Max Act: 0.1262. Min Act: -0.0001

Data Index: 44172 (C4 (Web Text))

Max Activating Token Index: 49

Text #1

Max Range: 0.1262. Min Range: -0.1262

Max Act: 0.1204. Min Act: -0.0001

Data Index: 330528 (C4 (Web Text))

Max Activating Token Index: 320

Text #2

Max Range: 0.1262. Min Range: -0.1262

Max Act: 0.1177. Min Act: -0.0001

Data Index: 224781 (C4 (Web Text))

Max Activating Token Index: 39

Text #3

Max Range: 0.1262. Min Range: -0.1262

Max Act: 0.1254. Min Act: -0.0001

Data Index: 845007 (C4 (Web Text))

Max Activating Token Index: 777

Text #4

Max Range: 0.1262. Min Range: -0.1262

Max Act: 0.1160. Min Act: -0.0001

Data Index: 918756 (C4 (Web Text))

Max Activating Token Index: 187

Text #5

Max Range: 0.1262. Min Range: -0.1262

Max Act: 0.1150. Min Act: -0.0001

Data Index: 1049468 (C4 (Web Text))

Max Activating Token Index: 721

Text #6

Max Range: 0.1262. Min Range: -0.1262

Max Act: 0.1129. Min Act: -0.0001

Data Index: 878025 (C4 (Web Text))

Max Activating Token Index: 940

Text #7

Max Range: 0.1262. Min Range: -0.1262

Max Act: 0.1067. Min Act: -0.0001

Data Index: 66437 (C4 (Web Text))

Max Activating Token Index: 822

Text #8

Max Range: 0.1262. Min Range: -0.1262

Max Act: 0.1011. Min Act: -0.0001

Data Index: 135746 (C4 (Web Text))

Max Activating Token Index: 216

Text #9

Max Range: 0.1262. Min Range: -0.1262

Max Act: 0.1113. Min Act: -0.0000

Data Index: 754159 (C4 (Web Text))

Max Activating Token Index: 954

Text #10

Max Range: 0.1262. Min Range: -0.1262

Max Act: 0.1024. Min Act: -0.0001

Data Index: 345997 (C4 (Web Text))

Max Activating Token Index: 645

Text #11

Max Range: 0.1262. Min Range: -0.1262

Max Act: 0.1052. Min Act: -0.0001

Data Index: 1023317 (C4 (Web Text))

Max Activating Token Index: 357

Text #12

Max Range: 0.1262. Min Range: -0.1262

Max Act: 0.1011. Min Act: -0.0001

Data Index: 880187 (C4 (Web Text))

Max Activating Token Index: 438

Text #13

Max Range: 0.1262. Min Range: -0.1262

Max Act: 0.0921. Min Act: -0.0001

Data Index: 467636 (C4 (Web Text))

Max Activating Token Index: 916

Text #14

Max Range: 0.1262. Min Range: -0.1262

Max Act: 0.0952. Min Act: -0.0001

Data Index: 949990 (C4 (Web Text))

Max Activating Token Index: 186

Text #15

Max Range: 0.1262. Min Range: -0.1262

Max Act: 0.0931. Min Act: -0.0001

Data Index: 250764 (C4 (Web Text))

Max Activating Token Index: 387

Text #16

Max Range: 0.1262. Min Range: -0.1262

Max Act: 0.0835. Min Act: -0.0001

Data Index: 1147101 (C4 (Web Text))

Max Activating Token Index: 582

Text #17

Max Range: 0.1262. Min Range: -0.1262

Max Act: 0.0832. Min Act: -0.0001

Data Index: 447525 (C4 (Web Text))

Max Activating Token Index: 786

Text #18

Max Range: 0.1262. Min Range: -0.1262

Max Act: 0.0885. Min Act: -0.0000

Data Index: 405126 (C4 (Web Text))

Max Activating Token Index: 977

Text #19

Max Range: 0.1262. Min Range: -0.1262

Max Act: 0.0856. Min Act: -0.0001

Data Index: 1619863 (Python Code)

Max Activating Token Index: 319