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

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

Neuron 5744 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8342. Min Range: -0.8342

Max Act: 0.8342. Min Act: -0.0000

Data Index: 1380192 (Python Code)

Max Activating Token Index: 513

Text #1

Max Range: 0.8342. Min Range: -0.8342

Max Act: 0.7428. Min Act: -0.0000

Data Index: 1427016 (Python Code)

Max Activating Token Index: 585

Text #2

Max Range: 0.8342. Min Range: -0.8342

Max Act: 0.7608. Min Act: -0.0000

Data Index: 1598167 (Python Code)

Max Activating Token Index: 883

Text #3

Max Range: 0.8342. Min Range: -0.8342

Max Act: 0.7232. Min Act: -0.0000

Data Index: 1545628 (Python Code)

Max Activating Token Index: 983

Text #4

Max Range: 0.8342. Min Range: -0.8342

Max Act: 0.6928. Min Act: -0.0000

Data Index: 442795 (C4 (Web Text))

Max Activating Token Index: 165

Text #5

Max Range: 0.8342. Min Range: -0.8342

Max Act: 0.6631. Min Act: -0.0000

Data Index: 1632560 (Python Code)

Max Activating Token Index: 577

Text #6

Max Range: 0.8342. Min Range: -0.8342

Max Act: 0.6027. Min Act: -0.0000

Data Index: 1549067 (Python Code)

Max Activating Token Index: 91

Text #7

Max Range: 0.8342. Min Range: -0.8342

Max Act: 0.6221. Min Act: -0.0000

Data Index: 1573964 (Python Code)

Max Activating Token Index: 1020

Text #8

Max Range: 0.8342. Min Range: -0.8342

Max Act: 0.5674. Min Act: -0.0000

Data Index: 1446049 (Python Code)

Max Activating Token Index: 30

Text #9

Max Range: 0.8342. Min Range: -0.8342

Max Act: 0.6021. Min Act: -0.0000

Data Index: 199303 (C4 (Web Text))

Max Activating Token Index: 700

Text #10

Max Range: 0.8342. Min Range: -0.8342

Max Act: 0.6071. Min Act: -0.0000

Data Index: 1546336 (Python Code)

Max Activating Token Index: 498

Text #11

Max Range: 0.8342. Min Range: -0.8342

Max Act: 0.5954. Min Act: -0.0000

Data Index: 1473604 (Python Code)

Max Activating Token Index: 348

Text #12

Max Range: 0.8342. Min Range: -0.8342

Max Act: 0.5874. Min Act: -0.0000

Data Index: 1477319 (Python Code)

Max Activating Token Index: 852

Text #13

Max Range: 0.8342. Min Range: -0.8342

Max Act: 0.5981. Min Act: -0.0000

Data Index: 1616027 (Python Code)

Max Activating Token Index: 448

Text #14

Max Range: 0.8342. Min Range: -0.8342

Max Act: 0.5936. Min Act: -0.0000

Data Index: 1620675 (Python Code)

Max Activating Token Index: 47

Text #15

Max Range: 0.8342. Min Range: -0.8342

Max Act: 0.5705. Min Act: -0.0000

Data Index: 1571577 (Python Code)

Max Activating Token Index: 946

Text #16

Max Range: 0.8342. Min Range: -0.8342

Max Act: 0.5441. Min Act: -0.0000

Data Index: 1620221 (Python Code)

Max Activating Token Index: 623

Text #17

Max Range: 0.8342. Min Range: -0.8342

Max Act: 0.5033. Min Act: -0.0000

Data Index: 642064 (C4 (Web Text))

Max Activating Token Index: 280

Text #18

Max Range: 0.8342. Min Range: -0.8342

Max Act: 0.5385. Min Act: -0.0000

Data Index: 1453068 (Python Code)

Max Activating Token Index: 19

Text #19

Max Range: 0.8342. Min Range: -0.8342

Max Act: 0.5097. Min Act: -0.0000

Data Index: 1476203 (Python Code)

Max Activating Token Index: 704