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

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

Neuron 3922 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: 0.9088. Min Range: -0.9088

Max Act: 0.9088. Min Act: -0.0000

Data Index: 1613371 (Python Code)

Max Activating Token Index: 185

Text #1

Max Range: 0.9088. Min Range: -0.9088

Max Act: 0.8818. Min Act: -0.0000

Data Index: 1384731 (Python Code)

Max Activating Token Index: 290

Text #2

Max Range: 0.9088. Min Range: -0.9088

Max Act: 0.8164. Min Act: -0.0000

Data Index: 1553630 (Python Code)

Max Activating Token Index: 563

Text #3

Max Range: 0.9088. Min Range: -0.9088

Max Act: 0.8358. Min Act: -0.0000

Data Index: 1429069 (Python Code)

Max Activating Token Index: 72

Text #4

Max Range: 0.9088. Min Range: -0.9088

Max Act: 0.7912. Min Act: -0.0001

Data Index: 1465282 (Python Code)

Max Activating Token Index: 158

Text #5

Max Range: 0.9088. Min Range: -0.9088

Max Act: 0.7947. Min Act: -0.0001

Data Index: 1540320 (Python Code)

Max Activating Token Index: 189

Text #6

Max Range: 0.9088. Min Range: -0.9088

Max Act: 0.7832. Min Act: -0.0001

Data Index: 328419 (C4 (Web Text))

Max Activating Token Index: 163

Text #7

Max Range: 0.9088. Min Range: -0.9088

Max Act: 0.6839. Min Act: -0.0001

Data Index: 1626031 (Python Code)

Max Activating Token Index: 278

Text #8

Max Range: 0.9088. Min Range: -0.9088

Max Act: 0.7467. Min Act: -0.0001

Data Index: 1394159 (Python Code)

Max Activating Token Index: 369

Text #9

Max Range: 0.9088. Min Range: -0.9088

Max Act: 0.7317. Min Act: -0.0001

Data Index: 1563250 (Python Code)

Max Activating Token Index: 248

Text #10

Max Range: 0.9088. Min Range: -0.9088

Max Act: 0.7269. Min Act: -0.0000

Data Index: 1362971 (Python Code)

Max Activating Token Index: 939

Text #11

Max Range: 0.9088. Min Range: -0.9088

Max Act: 0.7549. Min Act: -0.0000

Data Index: 1456792 (Python Code)

Max Activating Token Index: 264

Text #12

Max Range: 0.9088. Min Range: -0.9088

Max Act: 0.6649. Min Act: -0.0000

Data Index: 1411373 (Python Code)

Max Activating Token Index: 799

Text #13

Max Range: 0.9088. Min Range: -0.9088

Max Act: 0.6827. Min Act: -0.0000

Data Index: 1552174 (Python Code)

Max Activating Token Index: 638

Text #14

Max Range: 0.9088. Min Range: -0.9088

Max Act: 0.7211. Min Act: -0.0000

Data Index: 1559977 (Python Code)

Max Activating Token Index: 330

Text #15

Max Range: 0.9088. Min Range: -0.9088

Max Act: 0.7017. Min Act: -0.0000

Data Index: 1403514 (Python Code)

Max Activating Token Index: 176

Text #16

Max Range: 0.9088. Min Range: -0.9088

Max Act: 0.7401. Min Act: -0.0000

Data Index: 1600742 (Python Code)

Max Activating Token Index: 233

Text #17

Max Range: 0.9088. Min Range: -0.9088

Max Act: 0.7280. Min Act: -0.0000

Data Index: 1412311 (Python Code)

Max Activating Token Index: 563

Text #18

Max Range: 0.9088. Min Range: -0.9088

Max Act: 0.6801. Min Act: -0.0001

Data Index: 1438645 (Python Code)

Max Activating Token Index: 114

Text #19

Max Range: 0.9088. Min Range: -0.9088

Max Act: 0.6942. Min Act: -0.0001

Data Index: 1414223 (Python Code)

Max Activating Token Index: 85