Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3369 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9598. Min Range: -0.9598

Max Act: 0.9598. Min Act: -0.0000

Data Index: 1565574 (Python Code)

Max Activating Token Index: 650

Text #1

Max Range: 0.9598. Min Range: -0.9598

Max Act: 0.8202. Min Act: -0.0000

Data Index: 1503170 (Python Code)

Max Activating Token Index: 267

Text #2

Max Range: 0.9598. Min Range: -0.9598

Max Act: 0.8944. Min Act: 0.0000

Data Index: 1628864 (Python Code)

Max Activating Token Index: 92

Text #3

Max Range: 0.9598. Min Range: -0.9598

Max Act: 0.8541. Min Act: -0.0000

Data Index: 1643536 (Python Code)

Max Activating Token Index: 353

Text #4

Max Range: 0.9598. Min Range: -0.9598

Max Act: 0.6943. Min Act: -0.0000

Data Index: 1415291 (Python Code)

Max Activating Token Index: 989

Text #5

Max Range: 0.9598. Min Range: -0.9598

Max Act: 0.7194. Min Act: -0.0000

Data Index: 1637825 (Python Code)

Max Activating Token Index: 164

Text #6

Max Range: 0.9598. Min Range: -0.9598

Max Act: 0.7978. Min Act: -0.0000

Data Index: 1415784 (Python Code)

Max Activating Token Index: 488

Text #7

Max Range: 0.9598. Min Range: -0.9598

Max Act: 0.5312. Min Act: -0.0000

Data Index: 1494464 (Python Code)

Max Activating Token Index: 232

Text #8

Max Range: 0.9598. Min Range: -0.9598

Max Act: 0.8710. Min Act: -0.0000

Data Index: 1639258 (Python Code)

Max Activating Token Index: 105

Text #9

Max Range: 0.9598. Min Range: -0.9598

Max Act: 0.7547. Min Act: -0.0000

Data Index: 1486292 (Python Code)

Max Activating Token Index: 509

Text #10

Max Range: 0.9598. Min Range: -0.9598

Max Act: 0.8262. Min Act: -0.0000

Data Index: 1504799 (Python Code)

Max Activating Token Index: 387

Text #11

Max Range: 0.9598. Min Range: -0.9598

Max Act: 0.6701. Min Act: -0.0000

Data Index: 1575953 (Python Code)

Max Activating Token Index: 265

Text #12

Max Range: 0.9598. Min Range: -0.9598

Max Act: 0.6780. Min Act: -0.0000

Data Index: 1656535 (Python Code)

Max Activating Token Index: 770

Text #13

Max Range: 0.9598. Min Range: -0.9598

Max Act: 0.7360. Min Act: -0.0000

Data Index: 1440743 (Python Code)

Max Activating Token Index: 481

Text #14

Max Range: 0.9598. Min Range: -0.9598

Max Act: 0.5898. Min Act: -0.0000

Data Index: 730093 (C4 (Web Text))

Max Activating Token Index: 223

Text #15

Max Range: 0.9598. Min Range: -0.9598

Max Act: 0.7308. Min Act: -0.0000

Data Index: 1514267 (Python Code)

Max Activating Token Index: 255

Text #16

Max Range: 0.9598. Min Range: -0.9598

Max Act: 0.6827. Min Act: -0.0000

Data Index: 1482285 (Python Code)

Max Activating Token Index: 730

Text #17

Max Range: 0.9598. Min Range: -0.9598

Max Act: 0.7617. Min Act: -0.0000

Data Index: 1518727 (Python Code)

Max Activating Token Index: 458

Text #18

Max Range: 0.9598. Min Range: -0.9598

Max Act: 0.5427. Min Act: -0.0000

Data Index: 1517250 (Python Code)

Max Activating Token Index: 280

Text #19

Max Range: 0.9598. Min Range: -0.9598

Max Act: 0.6586. Min Act: -0.0000

Data Index: 878587 (C4 (Web Text))

Max Activating Token Index: 492