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

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

Neuron 170 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8166. Min Range: -3.8166

Max Act: 3.5033. Min Act: -0.0001

Data Index: 1431735 (Python Code)

Max Activating Token Index: 784

Text #1

Max Range: 3.8166. Min Range: -3.8166

Max Act: 3.8166. Min Act: -0.0001

Data Index: 1645583 (Python Code)

Max Activating Token Index: 730

Text #2

Max Range: 3.8166. Min Range: -3.8166

Max Act: 3.6010. Min Act: -0.0001

Data Index: 1438571 (Python Code)

Max Activating Token Index: 333

Text #3

Max Range: 3.8166. Min Range: -3.8166

Max Act: 3.5686. Min Act: -0.0001

Data Index: 328281 (C4 (Web Text))

Max Activating Token Index: 204

Text #4

Max Range: 3.8166. Min Range: -3.8166

Max Act: 3.1703. Min Act: -0.0001

Data Index: 1392124 (Python Code)

Max Activating Token Index: 173

Text #5

Max Range: 3.8166. Min Range: -3.8166

Max Act: 3.4686. Min Act: -0.0001

Data Index: 1645602 (Python Code)

Max Activating Token Index: 512

Text #6

Max Range: 3.8166. Min Range: -3.8166

Max Act: 3.5658. Min Act: -0.0001

Data Index: 1241849 (C4 (Web Text))

Max Activating Token Index: 311

Text #7

Max Range: 3.8166. Min Range: -3.8166

Max Act: 3.4972. Min Act: -0.0001

Data Index: 463258 (C4 (Web Text))

Max Activating Token Index: 227

Text #8

Max Range: 3.8166. Min Range: -3.8166

Max Act: 3.4356. Min Act: -0.0001

Data Index: 1479589 (Python Code)

Max Activating Token Index: 531

Text #9

Max Range: 3.8166. Min Range: -3.8166

Max Act: 3.0892. Min Act: -0.0001

Data Index: 1394849 (Python Code)

Max Activating Token Index: 762

Text #10

Max Range: 3.8166. Min Range: -3.8166

Max Act: 3.2249. Min Act: -0.0001

Data Index: 1367964 (Python Code)

Max Activating Token Index: 211

Text #11

Max Range: 3.8166. Min Range: -3.8166

Max Act: 3.2199. Min Act: -0.0001

Data Index: 1648842 (Python Code)

Max Activating Token Index: 34

Text #12

Max Range: 3.8166. Min Range: -3.8166

Max Act: 3.0541. Min Act: -0.0001

Data Index: 1499843 (Python Code)

Max Activating Token Index: 598

Text #13

Max Range: 3.8166. Min Range: -3.8166

Max Act: 3.3304. Min Act: -0.0001

Data Index: 1473781 (Python Code)

Max Activating Token Index: 772

Text #14

Max Range: 3.8166. Min Range: -3.8166

Max Act: 3.2953. Min Act: -0.0001

Data Index: 1182453 (C4 (Web Text))

Max Activating Token Index: 761

Text #15

Max Range: 3.8166. Min Range: -3.8166

Max Act: 3.1796. Min Act: -0.0001

Data Index: 1636988 (Python Code)

Max Activating Token Index: 391

Text #16

Max Range: 3.8166. Min Range: -3.8166

Max Act: 3.3349. Min Act: -0.0001

Data Index: 1535334 (Python Code)

Max Activating Token Index: 169

Text #17

Max Range: 3.8166. Min Range: -3.8166

Max Act: 2.8865. Min Act: -0.0001

Data Index: 1368938 (Python Code)

Max Activating Token Index: 172

Text #18

Max Range: 3.8166. Min Range: -3.8166

Max Act: 3.1977. Min Act: -0.0001

Data Index: 453959 (C4 (Web Text))

Max Activating Token Index: 640

Text #19

Max Range: 3.8166. Min Range: -3.8166

Max Act: 2.9439. Min Act: -0.0001

Data Index: 515847 (C4 (Web Text))

Max Activating Token Index: 71