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

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

Neuron 4585 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: 0.1511. Min Range: -0.1511

Max Act: 0.1511. Min Act: -0.0001

Data Index: 1512880 (Python Code)

Max Activating Token Index: 817

Text #1

Max Range: 0.1511. Min Range: -0.1511

Max Act: 0.1186. Min Act: -0.0001

Data Index: 1518724 (Python Code)

Max Activating Token Index: 41

Text #2

Max Range: 0.1511. Min Range: -0.1511

Max Act: 0.1191. Min Act: -0.0001

Data Index: 1592861 (Python Code)

Max Activating Token Index: 327

Text #3

Max Range: 0.1511. Min Range: -0.1511

Max Act: 0.1168. Min Act: -0.0001

Data Index: 1485226 (Python Code)

Max Activating Token Index: 65

Text #4

Max Range: 0.1511. Min Range: -0.1511

Max Act: 0.1135. Min Act: -0.0001

Data Index: 1077539 (C4 (Web Text))

Max Activating Token Index: 38

Text #5

Max Range: 0.1511. Min Range: -0.1511

Max Act: 0.1207. Min Act: -0.0001

Data Index: 1634696 (Python Code)

Max Activating Token Index: 229

Text #6

Max Range: 0.1511. Min Range: -0.1511

Max Act: 0.1245. Min Act: -0.0001

Data Index: 1645942 (Python Code)

Max Activating Token Index: 258

Text #7

Max Range: 0.1511. Min Range: -0.1511

Max Act: 0.1087. Min Act: -0.0001

Data Index: 1584799 (Python Code)

Max Activating Token Index: 139

Text #8

Max Range: 0.1511. Min Range: -0.1511

Max Act: 0.1085. Min Act: -0.0001

Data Index: 1591521 (Python Code)

Max Activating Token Index: 624

Text #9

Max Range: 0.1511. Min Range: -0.1511

Max Act: 0.1061. Min Act: -0.0001

Data Index: 1422064 (Python Code)

Max Activating Token Index: 134

Text #10

Max Range: 0.1511. Min Range: -0.1511

Max Act: 0.1061. Min Act: -0.0001

Data Index: 1101997 (C4 (Web Text))

Max Activating Token Index: 77

Text #11

Max Range: 0.1511. Min Range: -0.1511

Max Act: 0.1053. Min Act: -0.0001

Data Index: 1529292 (Python Code)

Max Activating Token Index: 543

Text #12

Max Range: 0.1511. Min Range: -0.1511

Max Act: 0.1123. Min Act: -0.0001

Data Index: 115005 (C4 (Web Text))

Max Activating Token Index: 80

Text #13

Max Range: 0.1511. Min Range: -0.1511

Max Act: 0.1049. Min Act: -0.0001

Data Index: 1534723 (Python Code)

Max Activating Token Index: 324

Text #14

Max Range: 0.1511. Min Range: -0.1511

Max Act: 0.1094. Min Act: -0.0001

Data Index: 673062 (C4 (Web Text))

Max Activating Token Index: 779

Text #15

Max Range: 0.1511. Min Range: -0.1511

Max Act: 0.1060. Min Act: -0.0001

Data Index: 290830 (C4 (Web Text))

Max Activating Token Index: 757

Text #16

Max Range: 0.1511. Min Range: -0.1511

Max Act: 0.0996. Min Act: -0.0001

Data Index: 1471526 (Python Code)

Max Activating Token Index: 941

Text #17

Max Range: 0.1511. Min Range: -0.1511

Max Act: 0.0941. Min Act: -0.0001

Data Index: 1590811 (Python Code)

Max Activating Token Index: 800

Text #18

Max Range: 0.1511. Min Range: -0.1511

Max Act: 0.0971. Min Act: -0.0001

Data Index: 1599297 (Python Code)

Max Activating Token Index: 702

Text #19

Max Range: 0.1511. Min Range: -0.1511

Max Act: 0.1002. Min Act: -0.0001

Data Index: 1482235 (Python Code)

Max Activating Token Index: 61