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

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

Neuron 5468 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: 2.1494. Min Range: -2.1494

Max Act: 2.1494. Min Act: -0.0000

Data Index: 1071026 (C4 (Web Text))

Max Activating Token Index: 794

Text #1

Max Range: 2.1494. Min Range: -2.1494

Max Act: 1.7211. Min Act: -0.0000

Data Index: 306160 (C4 (Web Text))

Max Activating Token Index: 41

Text #2

Max Range: 2.1494. Min Range: -2.1494

Max Act: 1.7996. Min Act: -0.0000

Data Index: 1486953 (Python Code)

Max Activating Token Index: 13

Text #3

Max Range: 2.1494. Min Range: -2.1494

Max Act: 1.7829. Min Act: -0.0000

Data Index: 1446139 (Python Code)

Max Activating Token Index: 452

Text #4

Max Range: 2.1494. Min Range: -2.1494

Max Act: 1.7358. Min Act: -0.0000

Data Index: 1616744 (Python Code)

Max Activating Token Index: 606

Text #5

Max Range: 2.1494. Min Range: -2.1494

Max Act: 1.7013. Min Act: -0.0000

Data Index: 280978 (C4 (Web Text))

Max Activating Token Index: 236

Text #6

Max Range: 2.1494. Min Range: -2.1494

Max Act: 1.6491. Min Act: -0.0000

Data Index: 1647333 (Python Code)

Max Activating Token Index: 785

Text #7

Max Range: 2.1494. Min Range: -2.1494

Max Act: 1.7025. Min Act: -0.0000

Data Index: 1504450 (Python Code)

Max Activating Token Index: 211

Text #8

Max Range: 2.1494. Min Range: -2.1494

Max Act: 1.5840. Min Act: -0.0000

Data Index: 1607001 (Python Code)

Max Activating Token Index: 781

Text #9

Max Range: 2.1494. Min Range: -2.1494

Max Act: 1.5483. Min Act: -0.0000

Data Index: 254981 (C4 (Web Text))

Max Activating Token Index: 9

Text #10

Max Range: 2.1494. Min Range: -2.1494

Max Act: 1.3988. Min Act: -0.0000

Data Index: 1411865 (Python Code)

Max Activating Token Index: 636

Text #11

Max Range: 2.1494. Min Range: -2.1494

Max Act: 1.5464. Min Act: -0.0000

Data Index: 1630269 (Python Code)

Max Activating Token Index: 114

Text #12

Max Range: 2.1494. Min Range: -2.1494

Max Act: 1.4551. Min Act: -0.0000

Data Index: 567773 (C4 (Web Text))

Max Activating Token Index: 853

Text #13

Max Range: 2.1494. Min Range: -2.1494

Max Act: 1.6318. Min Act: -0.0000

Data Index: 1558081 (Python Code)

Max Activating Token Index: 370

Text #14

Max Range: 2.1494. Min Range: -2.1494

Max Act: 1.6545. Min Act: -0.0000

Data Index: 1523278 (Python Code)

Max Activating Token Index: 342

Text #15

Max Range: 2.1494. Min Range: -2.1494

Max Act: 1.5072. Min Act: -0.0000

Data Index: 30094 (C4 (Web Text))

Max Activating Token Index: 310

Text #16

Max Range: 2.1494. Min Range: -2.1494

Max Act: 1.5280. Min Act: -0.0000

Data Index: 17756 (C4 (Web Text))

Max Activating Token Index: 75

Text #17

Max Range: 2.1494. Min Range: -2.1494

Max Act: 1.4382. Min Act: -0.0000

Data Index: 329087 (C4 (Web Text))

Max Activating Token Index: 786

Text #18

Max Range: 2.1494. Min Range: -2.1494

Max Act: 1.5141. Min Act: -0.0000

Data Index: 497366 (C4 (Web Text))

Max Activating Token Index: 182

Text #19

Max Range: 2.1494. Min Range: -2.1494

Max Act: 1.5990. Min Act: -0.0000

Data Index: 1547074 (Python Code)

Max Activating Token Index: 229