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

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

Neuron 1365 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3287. Min Range: -1.3287

Max Act: 1.3287. Min Act: 0.0000

Data Index: 867702 (C4 (Web Text))

Max Activating Token Index: 96

Text #1

Max Range: 1.3287. Min Range: -1.3287

Max Act: 0.8814. Min Act: 0.0000

Data Index: 615833 (C4 (Web Text))

Max Activating Token Index: 186

Text #2

Max Range: 1.3287. Min Range: -1.3287

Max Act: 0.9450. Min Act: -0.0000

Data Index: 1567088 (Python Code)

Max Activating Token Index: 1017

Text #3

Max Range: 1.3287. Min Range: -1.3287

Max Act: 0.8182. Min Act: -0.0000

Data Index: 1448694 (Python Code)

Max Activating Token Index: 823

Text #4

Max Range: 1.3287. Min Range: -1.3287

Max Act: 0.8471. Min Act: -0.0000

Data Index: 1424372 (Python Code)

Max Activating Token Index: 114

Text #5

Max Range: 1.3287. Min Range: -1.3287

Max Act: 0.7849. Min Act: -0.0000

Data Index: 1391915 (Python Code)

Max Activating Token Index: 90

Text #6

Max Range: 1.3287. Min Range: -1.3287

Max Act: 0.7999. Min Act: -0.0000

Data Index: 1364513 (Python Code)

Max Activating Token Index: 685

Text #7

Max Range: 1.3287. Min Range: -1.3287

Max Act: 0.8011. Min Act: -0.0000

Data Index: 1555027 (Python Code)

Max Activating Token Index: 805

Text #8

Max Range: 1.3287. Min Range: -1.3287

Max Act: 0.7748. Min Act: -0.0000

Data Index: 1247341 (C4 (Web Text))

Max Activating Token Index: 120

Text #9

Max Range: 1.3287. Min Range: -1.3287

Max Act: 0.8000. Min Act: -0.0000

Data Index: 173839 (C4 (Web Text))

Max Activating Token Index: 92

Text #10

Max Range: 1.3287. Min Range: -1.3287

Max Act: 0.7525. Min Act: -0.0000

Data Index: 1604771 (Python Code)

Max Activating Token Index: 882

Text #11

Max Range: 1.3287. Min Range: -1.3287

Max Act: 0.7534. Min Act: -0.0000

Data Index: 1400010 (Python Code)

Max Activating Token Index: 57

Text #12

Max Range: 1.3287. Min Range: -1.3287

Max Act: 0.7574. Min Act: -0.0000

Data Index: 1592702 (Python Code)

Max Activating Token Index: 835

Text #13

Max Range: 1.3287. Min Range: -1.3287

Max Act: 0.7497. Min Act: -0.0000

Data Index: 1587581 (Python Code)

Max Activating Token Index: 773

Text #14

Max Range: 1.3287. Min Range: -1.3287

Max Act: 0.7424. Min Act: -0.0000

Data Index: 1651032 (Python Code)

Max Activating Token Index: 881

Text #15

Max Range: 1.3287. Min Range: -1.3287

Max Act: 0.7168. Min Act: -0.0000

Data Index: 55930 (C4 (Web Text))

Max Activating Token Index: 472

Text #16

Max Range: 1.3287. Min Range: -1.3287

Max Act: 0.7514. Min Act: -0.0000

Data Index: 1585757 (Python Code)

Max Activating Token Index: 726

Text #17

Max Range: 1.3287. Min Range: -1.3287

Max Act: 0.7567. Min Act: -0.0000

Data Index: 1364239 (Python Code)

Max Activating Token Index: 547

Text #18

Max Range: 1.3287. Min Range: -1.3287

Max Act: 0.7673. Min Act: -0.0000

Data Index: 1456532 (Python Code)

Max Activating Token Index: 327

Text #19

Max Range: 1.3287. Min Range: -1.3287

Max Act: 0.7685. Min Act: -0.0000

Data Index: 1376718 (Python Code)

Max Activating Token Index: 793