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

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

Neuron 804 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1670. Min Act: -0.0000

Data Index: 1657046 (Python Code)

Max Activating Token Index: 694

Text #1

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1560. Min Act: -0.0000

Data Index: 509592 (C4 (Web Text))

Max Activating Token Index: 75

Text #2

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1273. Min Act: -0.0000

Data Index: 645896 (C4 (Web Text))

Max Activating Token Index: 101

Text #3

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1437. Min Act: -0.0000

Data Index: 1034395 (C4 (Web Text))

Max Activating Token Index: 23

Text #4

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1350. Min Act: -0.0000

Data Index: 1343517 (C4 (Web Text))

Max Activating Token Index: 34

Text #5

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1216. Min Act: -0.0000

Data Index: 790468 (C4 (Web Text))

Max Activating Token Index: 263

Text #6

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1280. Min Act: -0.0000

Data Index: 101304 (C4 (Web Text))

Max Activating Token Index: 12

Text #7

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1122. Min Act: -0.0000

Data Index: 906198 (C4 (Web Text))

Max Activating Token Index: 672

Text #8

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1310. Min Act: -0.0000

Data Index: 513949 (C4 (Web Text))

Max Activating Token Index: 99

Text #9

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1031. Min Act: -0.0000

Data Index: 1139161 (C4 (Web Text))

Max Activating Token Index: 610

Text #10

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1098. Min Act: -0.0000

Data Index: 112122 (C4 (Web Text))

Max Activating Token Index: 785

Text #11

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1094. Min Act: -0.0000

Data Index: 143145 (C4 (Web Text))

Max Activating Token Index: 204

Text #12

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1123. Min Act: -0.0000

Data Index: 684980 (C4 (Web Text))

Max Activating Token Index: 625

Text #13

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1034. Min Act: -0.0000

Data Index: 1167668 (C4 (Web Text))

Max Activating Token Index: 31

Text #14

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1174. Min Act: -0.0000

Data Index: 1315354 (C4 (Web Text))

Max Activating Token Index: 80

Text #15

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1090. Min Act: -0.0000

Data Index: 756112 (C4 (Web Text))

Max Activating Token Index: 104

Text #16

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1135. Min Act: -0.0000

Data Index: 779169 (C4 (Web Text))

Max Activating Token Index: 424

Text #17

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1033. Min Act: -0.0000

Data Index: 776159 (C4 (Web Text))

Max Activating Token Index: 63

Text #18

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1032. Min Act: -0.0000

Data Index: 1848 (C4 (Web Text))

Max Activating Token Index: 621

Text #19

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1118. Min Act: -0.0000

Data Index: 1336779 (C4 (Web Text))

Max Activating Token Index: 714