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

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

Neuron 5019 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1666. Min Range: -0.1666

Max Act: 0.1533. Min Act: -0.0001

Data Index: 1215640 (C4 (Web Text))

Max Activating Token Index: 268

Text #1

Max Range: 0.1666. Min Range: -0.1666

Max Act: 0.1666. Min Act: -0.0000

Data Index: 1069888 (C4 (Web Text))

Max Activating Token Index: 814

Text #2

Max Range: 0.1666. Min Range: -0.1666

Max Act: 0.1274. Min Act: -0.0000

Data Index: 1588965 (Python Code)

Max Activating Token Index: 13

Text #3

Max Range: 0.1666. Min Range: -0.1666

Max Act: 0.1180. Min Act: -0.0000

Data Index: 1603740 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 0.1666. Min Range: -0.1666

Max Act: 0.1223. Min Act: -0.0000

Data Index: 33449 (C4 (Web Text))

Max Activating Token Index: 103

Text #5

Max Range: 0.1666. Min Range: -0.1666

Max Act: 0.1084. Min Act: -0.0000

Data Index: 951350 (C4 (Web Text))

Max Activating Token Index: 70

Text #6

Max Range: 0.1666. Min Range: -0.1666

Max Act: 0.1116. Min Act: -0.0000

Data Index: 87398 (C4 (Web Text))

Max Activating Token Index: 72

Text #7

Max Range: 0.1666. Min Range: -0.1666

Max Act: 0.1110. Min Act: -0.0000

Data Index: 60776 (C4 (Web Text))

Max Activating Token Index: 64

Text #8

Max Range: 0.1666. Min Range: -0.1666

Max Act: 0.1100. Min Act: -0.0000

Data Index: 257784 (C4 (Web Text))

Max Activating Token Index: 46

Text #9

Max Range: 0.1666. Min Range: -0.1666

Max Act: 0.1066. Min Act: -0.0001

Data Index: 692534 (C4 (Web Text))

Max Activating Token Index: 133

Text #10

Max Range: 0.1666. Min Range: -0.1666

Max Act: 0.1052. Min Act: -0.0000

Data Index: 853498 (C4 (Web Text))

Max Activating Token Index: 29

Text #11

Max Range: 0.1666. Min Range: -0.1666

Max Act: 0.1119. Min Act: -0.0000

Data Index: 1244445 (C4 (Web Text))

Max Activating Token Index: 100

Text #12

Max Range: 0.1666. Min Range: -0.1666

Max Act: 0.1063. Min Act: -0.0000

Data Index: 1097744 (C4 (Web Text))

Max Activating Token Index: 78

Text #13

Max Range: 0.1666. Min Range: -0.1666

Max Act: 0.1020. Min Act: -0.0000

Data Index: 94389 (C4 (Web Text))

Max Activating Token Index: 173

Text #14

Max Range: 0.1666. Min Range: -0.1666

Max Act: 0.1054. Min Act: -0.0000

Data Index: 365654 (C4 (Web Text))

Max Activating Token Index: 16

Text #15

Max Range: 0.1666. Min Range: -0.1666

Max Act: 0.1080. Min Act: -0.0000

Data Index: 1239580 (C4 (Web Text))

Max Activating Token Index: 116

Text #16

Max Range: 0.1666. Min Range: -0.1666

Max Act: 0.1009. Min Act: -0.0000

Data Index: 1345375 (C4 (Web Text))

Max Activating Token Index: 298

Text #17

Max Range: 0.1666. Min Range: -0.1666

Max Act: 0.1062. Min Act: -0.0000

Data Index: 791397 (C4 (Web Text))

Max Activating Token Index: 14

Text #18

Max Range: 0.1666. Min Range: -0.1666

Max Act: 0.0921. Min Act: -0.0000

Data Index: 1611071 (Python Code)

Max Activating Token Index: 957

Text #19

Max Range: 0.1666. Min Range: -0.1666

Max Act: 0.0949. Min Act: -0.0000

Data Index: 979014 (C4 (Web Text))

Max Activating Token Index: 88