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

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

Neuron 1955 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6322. Min Range: -1.6322

Max Act: 1.6322. Min Act: -0.0000

Data Index: 435276 (C4 (Web Text))

Max Activating Token Index: 553

Text #1

Max Range: 1.6322. Min Range: -1.6322

Max Act: 1.4830. Min Act: -0.0000

Data Index: 1233198 (C4 (Web Text))

Max Activating Token Index: 66

Text #2

Max Range: 1.6322. Min Range: -1.6322

Max Act: 1.4381. Min Act: -0.0000

Data Index: 58290 (C4 (Web Text))

Max Activating Token Index: 515

Text #3

Max Range: 1.6322. Min Range: -1.6322

Max Act: 1.4410. Min Act: -0.0000

Data Index: 1472901 (Python Code)

Max Activating Token Index: 330

Text #4

Max Range: 1.6322. Min Range: -1.6322

Max Act: 1.3957. Min Act: -0.0000

Data Index: 125731 (C4 (Web Text))

Max Activating Token Index: 738

Text #5

Max Range: 1.6322. Min Range: -1.6322

Max Act: 1.3604. Min Act: -0.0000

Data Index: 390795 (C4 (Web Text))

Max Activating Token Index: 240

Text #6

Max Range: 1.6322. Min Range: -1.6322

Max Act: 1.2803. Min Act: -0.0000

Data Index: 986268 (C4 (Web Text))

Max Activating Token Index: 180

Text #7

Max Range: 1.6322. Min Range: -1.6322

Max Act: 1.4159. Min Act: -0.0000

Data Index: 649029 (C4 (Web Text))

Max Activating Token Index: 958

Text #8

Max Range: 1.6322. Min Range: -1.6322

Max Act: 1.2448. Min Act: -0.0000

Data Index: 144718 (C4 (Web Text))

Max Activating Token Index: 874

Text #9

Max Range: 1.6322. Min Range: -1.6322

Max Act: 1.1431. Min Act: -0.0000

Data Index: 534910 (C4 (Web Text))

Max Activating Token Index: 199

Text #10

Max Range: 1.6322. Min Range: -1.6322

Max Act: 1.0660. Min Act: -0.0000

Data Index: 961557 (C4 (Web Text))

Max Activating Token Index: 217

Text #11

Max Range: 1.6322. Min Range: -1.6322

Max Act: 1.2181. Min Act: -0.0000

Data Index: 244794 (C4 (Web Text))

Max Activating Token Index: 781

Text #12

Max Range: 1.6322. Min Range: -1.6322

Max Act: 1.2626. Min Act: -0.0000

Data Index: 107968 (C4 (Web Text))

Max Activating Token Index: 305

Text #13

Max Range: 1.6322. Min Range: -1.6322

Max Act: 1.1809. Min Act: -0.0000

Data Index: 372891 (C4 (Web Text))

Max Activating Token Index: 601

Text #14

Max Range: 1.6322. Min Range: -1.6322

Max Act: 1.1831. Min Act: -0.0000

Data Index: 347880 (C4 (Web Text))

Max Activating Token Index: 345

Text #15

Max Range: 1.6322. Min Range: -1.6322

Max Act: 1.0911. Min Act: -0.0000

Data Index: 1349824 (C4 (Web Text))

Max Activating Token Index: 620

Text #16

Max Range: 1.6322. Min Range: -1.6322

Max Act: 1.1518. Min Act: -0.0000

Data Index: 1459312 (Python Code)

Max Activating Token Index: 449

Text #17

Max Range: 1.6322. Min Range: -1.6322

Max Act: 1.1891. Min Act: -0.0000

Data Index: 752170 (C4 (Web Text))

Max Activating Token Index: 257

Text #18

Max Range: 1.6322. Min Range: -1.6322

Max Act: 1.0965. Min Act: -0.0000

Data Index: 1608233 (Python Code)

Max Activating Token Index: 664

Text #19

Max Range: 1.6322. Min Range: -1.6322

Max Act: 1.1781. Min Act: -0.0000

Data Index: 344546 (C4 (Web Text))

Max Activating Token Index: 493