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

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

Neuron 1772 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8787. Min Range: -0.8787

Max Act: 0.8787. Min Act: 0.0001

Data Index: 1604152 (Python Code)

Max Activating Token Index: 222

Text #1

Max Range: 0.8787. Min Range: -0.8787

Max Act: 0.8586. Min Act: -0.0000

Data Index: 1404413 (Python Code)

Max Activating Token Index: 507

Text #2

Max Range: 0.8787. Min Range: -0.8787

Max Act: 0.8743. Min Act: -0.0000

Data Index: 1419853 (Python Code)

Max Activating Token Index: 942

Text #3

Max Range: 0.8787. Min Range: -0.8787

Max Act: 0.8611. Min Act: 0.0001

Data Index: 1571748 (Python Code)

Max Activating Token Index: 257

Text #4

Max Range: 0.8787. Min Range: -0.8787

Max Act: 0.8372. Min Act: -0.0000

Data Index: 1564229 (Python Code)

Max Activating Token Index: 65

Text #5

Max Range: 0.8787. Min Range: -0.8787

Max Act: 0.7998. Min Act: -0.0000

Data Index: 1552762 (Python Code)

Max Activating Token Index: 625

Text #6

Max Range: 0.8787. Min Range: -0.8787

Max Act: 0.8561. Min Act: -0.0000

Data Index: 1614308 (Python Code)

Max Activating Token Index: 1016

Text #7

Max Range: 0.8787. Min Range: -0.8787

Max Act: 0.7817. Min Act: 0.0002

Data Index: 1645787 (Python Code)

Max Activating Token Index: 80

Text #8

Max Range: 0.8787. Min Range: -0.8787

Max Act: 0.7534. Min Act: 0.0000

Data Index: 1589276 (Python Code)

Max Activating Token Index: 165

Text #9

Max Range: 0.8787. Min Range: -0.8787

Max Act: 0.7370. Min Act: 0.0001

Data Index: 1525428 (Python Code)

Max Activating Token Index: 108

Text #10

Max Range: 0.8787. Min Range: -0.8787

Max Act: 0.7044. Min Act: 0.0000

Data Index: 1567767 (Python Code)

Max Activating Token Index: 621

Text #11

Max Range: 0.8787. Min Range: -0.8787

Max Act: 0.6639. Min Act: 0.0000

Data Index: 1650045 (Python Code)

Max Activating Token Index: 129

Text #12

Max Range: 0.8787. Min Range: -0.8787

Max Act: 0.7152. Min Act: 0.0001

Data Index: 1481160 (Python Code)

Max Activating Token Index: 318

Text #13

Max Range: 0.8787. Min Range: -0.8787

Max Act: 0.6671. Min Act: 0.0000

Data Index: 1571401 (Python Code)

Max Activating Token Index: 667

Text #14

Max Range: 0.8787. Min Range: -0.8787

Max Act: 0.6912. Min Act: 0.0001

Data Index: 1561717 (Python Code)

Max Activating Token Index: 238

Text #15

Max Range: 0.8787. Min Range: -0.8787

Max Act: 0.6634. Min Act: -0.0000

Data Index: 1534668 (Python Code)

Max Activating Token Index: 1007

Text #16

Max Range: 0.8787. Min Range: -0.8787

Max Act: 0.6463. Min Act: -0.0000

Data Index: 519273 (C4 (Web Text))

Max Activating Token Index: 179

Text #17

Max Range: 0.8787. Min Range: -0.8787

Max Act: 0.6786. Min Act: 0.0001

Data Index: 1493551 (Python Code)

Max Activating Token Index: 857

Text #18

Max Range: 0.8787. Min Range: -0.8787

Max Act: 0.6713. Min Act: -0.0000

Data Index: 1502880 (Python Code)

Max Activating Token Index: 537

Text #19

Max Range: 0.8787. Min Range: -0.8787

Max Act: 0.6742. Min Act: -0.0000

Data Index: 1654068 (Python Code)

Max Activating Token Index: 153