Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1879 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.8233. Min Range: -1.8233

Max Act: 1.8233. Min Act: -0.0001

Data Index: 1378462 (Python Code)

Max Activating Token Index: 173

Text #1

Max Range: 1.8233. Min Range: -1.8233

Max Act: 1.4181. Min Act: -0.0000

Data Index: 292068 (C4 (Web Text))

Max Activating Token Index: 701

Text #2

Max Range: 1.8233. Min Range: -1.8233

Max Act: 1.4374. Min Act: -0.0001

Data Index: 1434998 (Python Code)

Max Activating Token Index: 532

Text #3

Max Range: 1.8233. Min Range: -1.8233

Max Act: 1.3999. Min Act: -0.0000

Data Index: 1542492 (Python Code)

Max Activating Token Index: 147

Text #4

Max Range: 1.8233. Min Range: -1.8233

Max Act: 1.3249. Min Act: -0.0000

Data Index: 1342470 (C4 (Web Text))

Max Activating Token Index: 285

Text #5

Max Range: 1.8233. Min Range: -1.8233

Max Act: 1.2883. Min Act: -0.0000

Data Index: 1436150 (Python Code)

Max Activating Token Index: 363

Text #6

Max Range: 1.8233. Min Range: -1.8233

Max Act: 1.1812. Min Act: -0.0000

Data Index: 901912 (C4 (Web Text))

Max Activating Token Index: 415

Text #7

Max Range: 1.8233. Min Range: -1.8233

Max Act: 1.1911. Min Act: -0.0001

Data Index: 1446422 (Python Code)

Max Activating Token Index: 765

Text #8

Max Range: 1.8233. Min Range: -1.8233

Max Act: 1.1736. Min Act: 0.0002

Data Index: 1308965 (C4 (Web Text))

Max Activating Token Index: 269

Text #9

Max Range: 1.8233. Min Range: -1.8233

Max Act: 1.1683. Min Act: -0.0000

Data Index: 1243489 (C4 (Web Text))

Max Activating Token Index: 156

Text #10

Max Range: 1.8233. Min Range: -1.8233

Max Act: 1.1591. Min Act: -0.0001

Data Index: 1386893 (Python Code)

Max Activating Token Index: 337

Text #11

Max Range: 1.8233. Min Range: -1.8233

Max Act: 1.0782. Min Act: -0.0001

Data Index: 1413961 (Python Code)

Max Activating Token Index: 764

Text #12

Max Range: 1.8233. Min Range: -1.8233

Max Act: 1.1071. Min Act: -0.0001

Data Index: 1146476 (C4 (Web Text))

Max Activating Token Index: 495

Text #13

Max Range: 1.8233. Min Range: -1.8233

Max Act: 1.1826. Min Act: -0.0001

Data Index: 910060 (C4 (Web Text))

Max Activating Token Index: 829

Text #14

Max Range: 1.8233. Min Range: -1.8233

Max Act: 1.0994. Min Act: -0.0001

Data Index: 1588046 (Python Code)

Max Activating Token Index: 540

Text #15

Max Range: 1.8233. Min Range: -1.8233

Max Act: 1.1280. Min Act: -0.0001

Data Index: 1370953 (Python Code)

Max Activating Token Index: 862

Text #16

Max Range: 1.8233. Min Range: -1.8233

Max Act: 1.0873. Min Act: -0.0001

Data Index: 1184932 (C4 (Web Text))

Max Activating Token Index: 937

Text #17

Max Range: 1.8233. Min Range: -1.8233

Max Act: 1.0409. Min Act: -0.0000

Data Index: 1330881 (C4 (Web Text))

Max Activating Token Index: 945

Text #18

Max Range: 1.8233. Min Range: -1.8233

Max Act: 1.0938. Min Act: 0.0000

Data Index: 54791 (C4 (Web Text))

Max Activating Token Index: 275

Text #19

Max Range: 1.8233. Min Range: -1.8233

Max Act: 0.9978. Min Act: -0.0001

Data Index: 425447 (C4 (Web Text))

Max Activating Token Index: 135