Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1354 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.6766. Min Act: 0.0000

Data Index: 1411899 (Python Code)

Max Activating Token Index: 720

Text #1

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.6967. Min Act: 0.0000

Data Index: 1399963 (Python Code)

Max Activating Token Index: 77

Text #2

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.6170. Min Act: 0.0000

Data Index: 1516473 (Python Code)

Max Activating Token Index: 563

Text #3

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.6859. Min Act: -0.0000

Data Index: 1607989 (Python Code)

Max Activating Token Index: 1003

Text #4

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.6596. Min Act: 0.0001

Data Index: 1470430 (Python Code)

Max Activating Token Index: 169

Text #5

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.6388. Min Act: 0.0000

Data Index: 1555604 (Python Code)

Max Activating Token Index: 229

Text #6

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.6394. Min Act: -0.0000

Data Index: 1499315 (Python Code)

Max Activating Token Index: 480

Text #7

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.5827. Min Act: -0.0001

Data Index: 1589918 (Python Code)

Max Activating Token Index: 256

Text #8

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.6121. Min Act: -0.0000

Data Index: 1545579 (Python Code)

Max Activating Token Index: 974

Text #9

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.5865. Min Act: -0.0001

Data Index: 1556559 (Python Code)

Max Activating Token Index: 737

Text #10

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.5873. Min Act: -0.0001

Data Index: 1417866 (Python Code)

Max Activating Token Index: 496

Text #11

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.5497. Min Act: -0.0001

Data Index: 1601861 (Python Code)

Max Activating Token Index: 446

Text #12

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.5483. Min Act: -0.0000

Data Index: 1511150 (Python Code)

Max Activating Token Index: 380

Text #13

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.5955. Min Act: -0.0000

Data Index: 1440118 (Python Code)

Max Activating Token Index: 565

Text #14

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.5590. Min Act: -0.0000

Data Index: 1471918 (Python Code)

Max Activating Token Index: 710

Text #15

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.5090. Min Act: -0.0001

Data Index: 1573889 (Python Code)

Max Activating Token Index: 699

Text #16

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.5560. Min Act: -0.0000

Data Index: 1404096 (Python Code)

Max Activating Token Index: 539

Text #17

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.5228. Min Act: -0.0000

Data Index: 1625115 (Python Code)

Max Activating Token Index: 388

Text #18

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.4876. Min Act: -0.0000

Data Index: 1510477 (Python Code)

Max Activating Token Index: 882

Text #19

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.5268. Min Act: -0.0000

Data Index: 1621985 (Python Code)

Max Activating Token Index: 196