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

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

Neuron 5382 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8002. Min Range: -0.8002

Max Act: 0.8002. Min Act: 0.0000

Data Index: 235740 (C4 (Web Text))

Max Activating Token Index: 27

Text #1

Max Range: 0.8002. Min Range: -0.8002

Max Act: 0.7181. Min Act: -0.0000

Data Index: 1409204 (Python Code)

Max Activating Token Index: 575

Text #2

Max Range: 0.8002. Min Range: -0.8002

Max Act: 0.7323. Min Act: -0.0000

Data Index: 1599611 (Python Code)

Max Activating Token Index: 370

Text #3

Max Range: 0.8002. Min Range: -0.8002

Max Act: 0.6841. Min Act: -0.0000

Data Index: 1396885 (Python Code)

Max Activating Token Index: 203

Text #4

Max Range: 0.8002. Min Range: -0.8002

Max Act: 0.6728. Min Act: -0.0000

Data Index: 1386415 (Python Code)

Max Activating Token Index: 309

Text #5

Max Range: 0.8002. Min Range: -0.8002

Max Act: 0.6633. Min Act: -0.0000

Data Index: 1548696 (Python Code)

Max Activating Token Index: 119

Text #6

Max Range: 0.8002. Min Range: -0.8002

Max Act: 0.6943. Min Act: -0.0000

Data Index: 1510304 (Python Code)

Max Activating Token Index: 67

Text #7

Max Range: 0.8002. Min Range: -0.8002

Max Act: 0.6830. Min Act: -0.0000

Data Index: 1569861 (Python Code)

Max Activating Token Index: 974

Text #8

Max Range: 0.8002. Min Range: -0.8002

Max Act: 0.6776. Min Act: -0.0000

Data Index: 1469141 (Python Code)

Max Activating Token Index: 166

Text #9

Max Range: 0.8002. Min Range: -0.8002

Max Act: 0.6701. Min Act: -0.0000

Data Index: 1574563 (Python Code)

Max Activating Token Index: 934

Text #10

Max Range: 0.8002. Min Range: -0.8002

Max Act: 0.6460. Min Act: -0.0000

Data Index: 1532882 (Python Code)

Max Activating Token Index: 103

Text #11

Max Range: 0.8002. Min Range: -0.8002

Max Act: 0.6486. Min Act: -0.0000

Data Index: 1634350 (Python Code)

Max Activating Token Index: 342

Text #12

Max Range: 0.8002. Min Range: -0.8002

Max Act: 0.6274. Min Act: -0.0000

Data Index: 1619331 (Python Code)

Max Activating Token Index: 150

Text #13

Max Range: 0.8002. Min Range: -0.8002

Max Act: 0.6714. Min Act: -0.0000

Data Index: 575098 (C4 (Web Text))

Max Activating Token Index: 359

Text #14

Max Range: 0.8002. Min Range: -0.8002

Max Act: 0.6215. Min Act: -0.0000

Data Index: 1486226 (Python Code)

Max Activating Token Index: 36

Text #15

Max Range: 0.8002. Min Range: -0.8002

Max Act: 0.6042. Min Act: -0.0000

Data Index: 1388906 (Python Code)

Max Activating Token Index: 769

Text #16

Max Range: 0.8002. Min Range: -0.8002

Max Act: 0.6258. Min Act: -0.0000

Data Index: 1628937 (Python Code)

Max Activating Token Index: 1001

Text #17

Max Range: 0.8002. Min Range: -0.8002

Max Act: 0.6346. Min Act: -0.0000

Data Index: 7478 (C4 (Web Text))

Max Activating Token Index: 340

Text #18

Max Range: 0.8002. Min Range: -0.8002

Max Act: 0.6199. Min Act: -0.0000

Data Index: 1380522 (Python Code)

Max Activating Token Index: 998

Text #19

Max Range: 0.8002. Min Range: -0.8002

Max Act: 0.6498. Min Act: -0.0000

Data Index: 1546517 (Python Code)

Max Activating Token Index: 173