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

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

Neuron 3223 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0622. Min Range: -1.0622

Max Act: 1.0622. Min Act: -0.0000

Data Index: 394388 (C4 (Web Text))

Max Activating Token Index: 605

Text #1

Max Range: 1.0622. Min Range: -1.0622

Max Act: 0.8094. Min Act: -0.0000

Data Index: 1477111 (Python Code)

Max Activating Token Index: 658

Text #2

Max Range: 1.0622. Min Range: -1.0622

Max Act: 0.7389. Min Act: -0.0000

Data Index: 1381347 (Python Code)

Max Activating Token Index: 440

Text #3

Max Range: 1.0622. Min Range: -1.0622

Max Act: 0.8366. Min Act: -0.0000

Data Index: 1169957 (C4 (Web Text))

Max Activating Token Index: 672

Text #4

Max Range: 1.0622. Min Range: -1.0622

Max Act: 0.8881. Min Act: -0.0000

Data Index: 1120920 (C4 (Web Text))

Max Activating Token Index: 765

Text #5

Max Range: 1.0622. Min Range: -1.0622

Max Act: 0.8117. Min Act: -0.0000

Data Index: 1379633 (Python Code)

Max Activating Token Index: 918

Text #6

Max Range: 1.0622. Min Range: -1.0622

Max Act: 0.8498. Min Act: -0.0000

Data Index: 161362 (C4 (Web Text))

Max Activating Token Index: 233

Text #7

Max Range: 1.0622. Min Range: -1.0622

Max Act: 0.8402. Min Act: -0.0000

Data Index: 1533843 (Python Code)

Max Activating Token Index: 937

Text #8

Max Range: 1.0622. Min Range: -1.0622

Max Act: 0.7863. Min Act: -0.0000

Data Index: 1221111 (C4 (Web Text))

Max Activating Token Index: 26

Text #9

Max Range: 1.0622. Min Range: -1.0622

Max Act: 0.7487. Min Act: -0.0000

Data Index: 1636733 (Python Code)

Max Activating Token Index: 758

Text #10

Max Range: 1.0622. Min Range: -1.0622

Max Act: 0.7743. Min Act: -0.0000

Data Index: 1418001 (Python Code)

Max Activating Token Index: 948

Text #11

Max Range: 1.0622. Min Range: -1.0622

Max Act: 0.6621. Min Act: -0.0000

Data Index: 1410276 (Python Code)

Max Activating Token Index: 991

Text #12

Max Range: 1.0622. Min Range: -1.0622

Max Act: 0.7064. Min Act: -0.0000

Data Index: 828963 (C4 (Web Text))

Max Activating Token Index: 124

Text #13

Max Range: 1.0622. Min Range: -1.0622

Max Act: 0.7259. Min Act: -0.0000

Data Index: 1630857 (Python Code)

Max Activating Token Index: 847

Text #14

Max Range: 1.0622. Min Range: -1.0622

Max Act: 0.7594. Min Act: -0.0000

Data Index: 1457789 (Python Code)

Max Activating Token Index: 318

Text #15

Max Range: 1.0622. Min Range: -1.0622

Max Act: 0.6225. Min Act: -0.0000

Data Index: 1475117 (Python Code)

Max Activating Token Index: 200

Text #16

Max Range: 1.0622. Min Range: -1.0622

Max Act: 0.6503. Min Act: -0.0000

Data Index: 1354137 (C4 (Web Text))

Max Activating Token Index: 27

Text #17

Max Range: 1.0622. Min Range: -1.0622

Max Act: 0.6410. Min Act: -0.0000

Data Index: 1637930 (Python Code)

Max Activating Token Index: 872

Text #18

Max Range: 1.0622. Min Range: -1.0622

Max Act: 0.6799. Min Act: -0.0000

Data Index: 1508342 (Python Code)

Max Activating Token Index: 217

Text #19

Max Range: 1.0622. Min Range: -1.0622

Max Act: 0.6688. Min Act: -0.0000

Data Index: 107643 (C4 (Web Text))

Max Activating Token Index: 38