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

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

Neuron 1645 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0430. Min Range: -1.0430

Max Act: 1.0430. Min Act: -0.0000

Data Index: 1185218 (C4 (Web Text))

Max Activating Token Index: 112

Text #1

Max Range: 1.0430. Min Range: -1.0430

Max Act: 0.8930. Min Act: -0.0000

Data Index: 259140 (C4 (Web Text))

Max Activating Token Index: 601

Text #2

Max Range: 1.0430. Min Range: -1.0430

Max Act: 0.9824. Min Act: -0.0000

Data Index: 1402670 (Python Code)

Max Activating Token Index: 734

Text #3

Max Range: 1.0430. Min Range: -1.0430

Max Act: 0.9669. Min Act: -0.0000

Data Index: 837693 (C4 (Web Text))

Max Activating Token Index: 351

Text #4

Max Range: 1.0430. Min Range: -1.0430

Max Act: 0.9411. Min Act: -0.0000

Data Index: 1143267 (C4 (Web Text))

Max Activating Token Index: 233

Text #5

Max Range: 1.0430. Min Range: -1.0430

Max Act: 0.8964. Min Act: -0.0000

Data Index: 737054 (C4 (Web Text))

Max Activating Token Index: 260

Text #6

Max Range: 1.0430. Min Range: -1.0430

Max Act: 0.8586. Min Act: -0.0000

Data Index: 722505 (C4 (Web Text))

Max Activating Token Index: 155

Text #7

Max Range: 1.0430. Min Range: -1.0430

Max Act: 0.8318. Min Act: -0.0000

Data Index: 1361090 (Python Code)

Max Activating Token Index: 888

Text #8

Max Range: 1.0430. Min Range: -1.0430

Max Act: 0.8110. Min Act: -0.0000

Data Index: 259352 (C4 (Web Text))

Max Activating Token Index: 323

Text #9

Max Range: 1.0430. Min Range: -1.0430

Max Act: 0.9158. Min Act: -0.0000

Data Index: 1277593 (C4 (Web Text))

Max Activating Token Index: 365

Text #10

Max Range: 1.0430. Min Range: -1.0430

Max Act: 0.8392. Min Act: -0.0000

Data Index: 1382755 (Python Code)

Max Activating Token Index: 733

Text #11

Max Range: 1.0430. Min Range: -1.0430

Max Act: 0.8422. Min Act: -0.0000

Data Index: 864813 (C4 (Web Text))

Max Activating Token Index: 155

Text #12

Max Range: 1.0430. Min Range: -1.0430

Max Act: 0.8131. Min Act: -0.0000

Data Index: 1121165 (C4 (Web Text))

Max Activating Token Index: 100

Text #13

Max Range: 1.0430. Min Range: -1.0430

Max Act: 0.8347. Min Act: -0.0000

Data Index: 1392654 (Python Code)

Max Activating Token Index: 955

Text #14

Max Range: 1.0430. Min Range: -1.0430

Max Act: 0.8215. Min Act: -0.0000

Data Index: 583154 (C4 (Web Text))

Max Activating Token Index: 656

Text #15

Max Range: 1.0430. Min Range: -1.0430

Max Act: 0.8426. Min Act: -0.0000

Data Index: 410580 (C4 (Web Text))

Max Activating Token Index: 652

Text #16

Max Range: 1.0430. Min Range: -1.0430

Max Act: 0.7907. Min Act: -0.0000

Data Index: 202298 (C4 (Web Text))

Max Activating Token Index: 909

Text #17

Max Range: 1.0430. Min Range: -1.0430

Max Act: 0.7428. Min Act: -0.0000

Data Index: 816065 (C4 (Web Text))

Max Activating Token Index: 892

Text #18

Max Range: 1.0430. Min Range: -1.0430

Max Act: 0.7873. Min Act: -0.0000

Data Index: 1633786 (Python Code)

Max Activating Token Index: 677

Text #19

Max Range: 1.0430. Min Range: -1.0430

Max Act: 0.8356. Min Act: -0.0000

Data Index: 1215961 (C4 (Web Text))

Max Activating Token Index: 495