Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1242 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.2346. Min Range: -0.2346

Max Act: 0.2346. Min Act: -0.0002

Data Index: 1204211 (C4 (Web Text))

Max Activating Token Index: 997

Text #1

Max Range: 0.2346. Min Range: -0.2346

Max Act: 0.2320. Min Act: -0.0002

Data Index: 1552507 (Python Code)

Max Activating Token Index: 151

Text #2

Max Range: 0.2346. Min Range: -0.2346

Max Act: 0.2158. Min Act: -0.0003

Data Index: 1568992 (Python Code)

Max Activating Token Index: 529

Text #3

Max Range: 0.2346. Min Range: -0.2346

Max Act: 0.2162. Min Act: -0.0002

Data Index: 1531262 (Python Code)

Max Activating Token Index: 306

Text #4

Max Range: 0.2346. Min Range: -0.2346

Max Act: 0.2125. Min Act: -0.0003

Data Index: 1612008 (Python Code)

Max Activating Token Index: 85

Text #5

Max Range: 0.2346. Min Range: -0.2346

Max Act: 0.2086. Min Act: -0.0002

Data Index: 1518851 (Python Code)

Max Activating Token Index: 626

Text #6

Max Range: 0.2346. Min Range: -0.2346

Max Act: 0.2112. Min Act: -0.0002

Data Index: 1550719 (Python Code)

Max Activating Token Index: 287

Text #7

Max Range: 0.2346. Min Range: -0.2346

Max Act: 0.2109. Min Act: -0.0003

Data Index: 1446797 (Python Code)

Max Activating Token Index: 902

Text #8

Max Range: 0.2346. Min Range: -0.2346

Max Act: 0.2103. Min Act: -0.0003

Data Index: 1567798 (Python Code)

Max Activating Token Index: 851

Text #9

Max Range: 0.2346. Min Range: -0.2346

Max Act: 0.2077. Min Act: -0.0003

Data Index: 1546322 (Python Code)

Max Activating Token Index: 181

Text #10

Max Range: 0.2346. Min Range: -0.2346

Max Act: 0.2074. Min Act: -0.0003

Data Index: 1565486 (Python Code)

Max Activating Token Index: 985

Text #11

Max Range: 0.2346. Min Range: -0.2346

Max Act: 0.1991. Min Act: -0.0002

Data Index: 1390123 (Python Code)

Max Activating Token Index: 288

Text #12

Max Range: 0.2346. Min Range: -0.2346

Max Act: 0.2067. Min Act: -0.0003

Data Index: 446743 (C4 (Web Text))

Max Activating Token Index: 602

Text #13

Max Range: 0.2346. Min Range: -0.2346

Max Act: 0.2042. Min Act: -0.0002

Data Index: 591543 (C4 (Web Text))

Max Activating Token Index: 424

Text #14

Max Range: 0.2346. Min Range: -0.2346

Max Act: 0.2057. Min Act: -0.0002

Data Index: 1497249 (Python Code)

Max Activating Token Index: 989

Text #15

Max Range: 0.2346. Min Range: -0.2346

Max Act: 0.2045. Min Act: -0.0003

Data Index: 1462276 (Python Code)

Max Activating Token Index: 684

Text #16

Max Range: 0.2346. Min Range: -0.2346

Max Act: 0.2052. Min Act: -0.0002

Data Index: 1434862 (Python Code)

Max Activating Token Index: 360

Text #17

Max Range: 0.2346. Min Range: -0.2346

Max Act: 0.2038. Min Act: -0.0002

Data Index: 1493306 (Python Code)

Max Activating Token Index: 908

Text #18

Max Range: 0.2346. Min Range: -0.2346

Max Act: 0.1967. Min Act: -0.0002

Data Index: 1487451 (Python Code)

Max Activating Token Index: 539

Text #19

Max Range: 0.2346. Min Range: -0.2346

Max Act: 0.2045. Min Act: -0.0002

Data Index: 1623070 (Python Code)

Max Activating Token Index: 287