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

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

Neuron 242 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1322. Min Range: -2.1322

Max Act: 2.1322. Min Act: -0.0000

Data Index: 925560 (C4 (Web Text))

Max Activating Token Index: 527

Text #1

Max Range: 2.1322. Min Range: -2.1322

Max Act: 1.5631. Min Act: -0.0000

Data Index: 85710 (C4 (Web Text))

Max Activating Token Index: 1015

Text #2

Max Range: 2.1322. Min Range: -2.1322

Max Act: 1.5349. Min Act: -0.0000

Data Index: 1204641 (C4 (Web Text))

Max Activating Token Index: 880

Text #3

Max Range: 2.1322. Min Range: -2.1322

Max Act: 1.5195. Min Act: -0.0000

Data Index: 1243068 (C4 (Web Text))

Max Activating Token Index: 737

Text #4

Max Range: 2.1322. Min Range: -2.1322

Max Act: 1.4126. Min Act: -0.0000

Data Index: 1080000 (C4 (Web Text))

Max Activating Token Index: 1000

Text #5

Max Range: 2.1322. Min Range: -2.1322

Max Act: 1.4605. Min Act: -0.0000

Data Index: 319561 (C4 (Web Text))

Max Activating Token Index: 293

Text #6

Max Range: 2.1322. Min Range: -2.1322

Max Act: 1.4535. Min Act: -0.0000

Data Index: 669133 (C4 (Web Text))

Max Activating Token Index: 844

Text #7

Max Range: 2.1322. Min Range: -2.1322

Max Act: 1.4116. Min Act: -0.0000

Data Index: 182477 (C4 (Web Text))

Max Activating Token Index: 694

Text #8

Max Range: 2.1322. Min Range: -2.1322

Max Act: 1.3629. Min Act: -0.0000

Data Index: 1329557 (C4 (Web Text))

Max Activating Token Index: 516

Text #9

Max Range: 2.1322. Min Range: -2.1322

Max Act: 1.3510. Min Act: -0.0000

Data Index: 1226666 (C4 (Web Text))

Max Activating Token Index: 884

Text #10

Max Range: 2.1322. Min Range: -2.1322

Max Act: 1.3586. Min Act: -0.0000

Data Index: 499144 (C4 (Web Text))

Max Activating Token Index: 784

Text #11

Max Range: 2.1322. Min Range: -2.1322

Max Act: 1.2826. Min Act: -0.0000

Data Index: 256133 (C4 (Web Text))

Max Activating Token Index: 219

Text #12

Max Range: 2.1322. Min Range: -2.1322

Max Act: 1.3228. Min Act: -0.0000

Data Index: 1217435 (C4 (Web Text))

Max Activating Token Index: 435

Text #13

Max Range: 2.1322. Min Range: -2.1322

Max Act: 1.3212. Min Act: -0.0000

Data Index: 683491 (C4 (Web Text))

Max Activating Token Index: 387

Text #14

Max Range: 2.1322. Min Range: -2.1322

Max Act: 1.3180. Min Act: -0.0000

Data Index: 42960 (C4 (Web Text))

Max Activating Token Index: 737

Text #15

Max Range: 2.1322. Min Range: -2.1322

Max Act: 1.2143. Min Act: -0.0000

Data Index: 312138 (C4 (Web Text))

Max Activating Token Index: 784

Text #16

Max Range: 2.1322. Min Range: -2.1322

Max Act: 1.2717. Min Act: -0.0000

Data Index: 844082 (C4 (Web Text))

Max Activating Token Index: 644

Text #17

Max Range: 2.1322. Min Range: -2.1322

Max Act: 1.1914. Min Act: -0.0000

Data Index: 1245151 (C4 (Web Text))

Max Activating Token Index: 680

Text #18

Max Range: 2.1322. Min Range: -2.1322

Max Act: 1.2501. Min Act: -0.0000

Data Index: 1189610 (C4 (Web Text))

Max Activating Token Index: 502

Text #19

Max Range: 2.1322. Min Range: -2.1322

Max Act: 1.1688. Min Act: -0.0000

Data Index: 1301625 (C4 (Web Text))

Max Activating Token Index: 96