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

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

Neuron 3255 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: 2.2998. Min Range: -2.2998

Max Act: 2.2073. Min Act: -0.0000

Data Index: 1631247 (Python Code)

Max Activating Token Index: 576

Text #1

Max Range: 2.2998. Min Range: -2.2998

Max Act: 2.2998. Min Act: -0.0000

Data Index: 1633146 (Python Code)

Max Activating Token Index: 93

Text #2

Max Range: 2.2998. Min Range: -2.2998

Max Act: 2.0998. Min Act: -0.0000

Data Index: 1484331 (Python Code)

Max Activating Token Index: 713

Text #3

Max Range: 2.2998. Min Range: -2.2998

Max Act: 1.9999. Min Act: -0.0000

Data Index: 1647344 (Python Code)

Max Activating Token Index: 887

Text #4

Max Range: 2.2998. Min Range: -2.2998

Max Act: 1.9231. Min Act: -0.0000

Data Index: 1528436 (Python Code)

Max Activating Token Index: 51

Text #5

Max Range: 2.2998. Min Range: -2.2998

Max Act: 1.7947. Min Act: -0.0000

Data Index: 1605257 (Python Code)

Max Activating Token Index: 603

Text #6

Max Range: 2.2998. Min Range: -2.2998

Max Act: 1.8283. Min Act: -0.0000

Data Index: 1572201 (Python Code)

Max Activating Token Index: 247

Text #7

Max Range: 2.2998. Min Range: -2.2998

Max Act: 1.8187. Min Act: -0.0000

Data Index: 1408376 (Python Code)

Max Activating Token Index: 248

Text #8

Max Range: 2.2998. Min Range: -2.2998

Max Act: 1.7603. Min Act: -0.0000

Data Index: 1585475 (Python Code)

Max Activating Token Index: 134

Text #9

Max Range: 2.2998. Min Range: -2.2998

Max Act: 1.7470. Min Act: -0.0000

Data Index: 1459335 (Python Code)

Max Activating Token Index: 3

Text #10

Max Range: 2.2998. Min Range: -2.2998

Max Act: 1.6404. Min Act: -0.0000

Data Index: 1547908 (Python Code)

Max Activating Token Index: 560

Text #11

Max Range: 2.2998. Min Range: -2.2998

Max Act: 1.5799. Min Act: -0.0000

Data Index: 1606121 (Python Code)

Max Activating Token Index: 77

Text #12

Max Range: 2.2998. Min Range: -2.2998

Max Act: 1.6728. Min Act: -0.0000

Data Index: 1466551 (Python Code)

Max Activating Token Index: 182

Text #13

Max Range: 2.2998. Min Range: -2.2998

Max Act: 1.6606. Min Act: -0.0000

Data Index: 1651423 (Python Code)

Max Activating Token Index: 615

Text #14

Max Range: 2.2998. Min Range: -2.2998

Max Act: 1.6429. Min Act: -0.0000

Data Index: 1596531 (Python Code)

Max Activating Token Index: 17

Text #15

Max Range: 2.2998. Min Range: -2.2998

Max Act: 1.6272. Min Act: -0.0000

Data Index: 1643577 (Python Code)

Max Activating Token Index: 114

Text #16

Max Range: 2.2998. Min Range: -2.2998

Max Act: 1.5389. Min Act: -0.0000

Data Index: 1420653 (Python Code)

Max Activating Token Index: 32

Text #17

Max Range: 2.2998. Min Range: -2.2998

Max Act: 1.6211. Min Act: -0.0000

Data Index: 1434571 (Python Code)

Max Activating Token Index: 345

Text #18

Max Range: 2.2998. Min Range: -2.2998

Max Act: 1.6254. Min Act: -0.0000

Data Index: 1494305 (Python Code)

Max Activating Token Index: 569

Text #19

Max Range: 2.2998. Min Range: -2.2998

Max Act: 1.7150. Min Act: -0.0000

Data Index: 1548277 (Python Code)

Max Activating Token Index: 713