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

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

Neuron 4988 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: 0.9299. Min Range: -0.9299

Max Act: 0.9299. Min Act: -0.0000

Data Index: 1524145 (Python Code)

Max Activating Token Index: 318

Text #1

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.9266. Min Act: -0.0001

Data Index: 1555295 (Python Code)

Max Activating Token Index: 301

Text #2

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.8807. Min Act: -0.0000

Data Index: 1424105 (Python Code)

Max Activating Token Index: 794

Text #3

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.8250. Min Act: -0.0000

Data Index: 1634570 (Python Code)

Max Activating Token Index: 592

Text #4

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.8706. Min Act: -0.0000

Data Index: 76352 (C4 (Web Text))

Max Activating Token Index: 162

Text #5

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.8484. Min Act: -0.0000

Data Index: 742796 (C4 (Web Text))

Max Activating Token Index: 187

Text #6

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.8458. Min Act: -0.0001

Data Index: 1650274 (Python Code)

Max Activating Token Index: 88

Text #7

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.8142. Min Act: -0.0000

Data Index: 1457589 (Python Code)

Max Activating Token Index: 121

Text #8

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.7661. Min Act: -0.0000

Data Index: 1544539 (Python Code)

Max Activating Token Index: 666

Text #9

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.8306. Min Act: -0.0000

Data Index: 1637664 (Python Code)

Max Activating Token Index: 700

Text #10

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.7911. Min Act: -0.0000

Data Index: 1435844 (Python Code)

Max Activating Token Index: 953

Text #11

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.6980. Min Act: -0.0000

Data Index: 1593243 (Python Code)

Max Activating Token Index: 709

Text #12

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.7475. Min Act: -0.0000

Data Index: 1642065 (Python Code)

Max Activating Token Index: 192

Text #13

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.6337. Min Act: -0.0000

Data Index: 1449116 (Python Code)

Max Activating Token Index: 157

Text #14

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.7232. Min Act: -0.0000

Data Index: 1580754 (Python Code)

Max Activating Token Index: 569

Text #15

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.7665. Min Act: -0.0000

Data Index: 1487107 (Python Code)

Max Activating Token Index: 392

Text #16

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.6944. Min Act: -0.0000

Data Index: 1547841 (Python Code)

Max Activating Token Index: 372

Text #17

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.6640. Min Act: -0.0000

Data Index: 1420049 (Python Code)

Max Activating Token Index: 174

Text #18

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.6453. Min Act: -0.0001

Data Index: 1381568 (Python Code)

Max Activating Token Index: 840

Text #19

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.6970. Min Act: -0.0000

Data Index: 1402268 (Python Code)

Max Activating Token Index: 574