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

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

Neuron 3825 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1835. Min Act: -0.0000

Data Index: 1101641 (C4 (Web Text))

Max Activating Token Index: 859

Text #1

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1994. Min Act: -0.0000

Data Index: 334964 (C4 (Web Text))

Max Activating Token Index: 205

Text #2

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1737. Min Act: -0.0000

Data Index: 229233 (C4 (Web Text))

Max Activating Token Index: 795

Text #3

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1871. Min Act: -0.0001

Data Index: 30241 (C4 (Web Text))

Max Activating Token Index: 595

Text #4

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1779. Min Act: -0.0000

Data Index: 1307903 (C4 (Web Text))

Max Activating Token Index: 77

Text #5

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1705. Min Act: -0.0000

Data Index: 303755 (C4 (Web Text))

Max Activating Token Index: 534

Text #6

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1715. Min Act: -0.0000

Data Index: 506176 (C4 (Web Text))

Max Activating Token Index: 997

Text #7

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1519. Min Act: -0.0000

Data Index: 399961 (C4 (Web Text))

Max Activating Token Index: 220

Text #8

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1663. Min Act: -0.0000

Data Index: 1313374 (C4 (Web Text))

Max Activating Token Index: 672

Text #9

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1541. Min Act: -0.0000

Data Index: 660910 (C4 (Web Text))

Max Activating Token Index: 353

Text #10

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1596. Min Act: -0.0000

Data Index: 292272 (C4 (Web Text))

Max Activating Token Index: 200

Text #11

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1529. Min Act: -0.0000

Data Index: 624269 (C4 (Web Text))

Max Activating Token Index: 438

Text #12

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1473. Min Act: -0.0000

Data Index: 1069478 (C4 (Web Text))

Max Activating Token Index: 966

Text #13

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1506. Min Act: -0.0000

Data Index: 766640 (C4 (Web Text))

Max Activating Token Index: 845

Text #14

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1496. Min Act: -0.0000

Data Index: 1031054 (C4 (Web Text))

Max Activating Token Index: 981

Text #15

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1507. Min Act: -0.0000

Data Index: 28829 (C4 (Web Text))

Max Activating Token Index: 621

Text #16

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1551. Min Act: -0.0000

Data Index: 1059054 (C4 (Web Text))

Max Activating Token Index: 56

Text #17

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1477. Min Act: -0.0001

Data Index: 906844 (C4 (Web Text))

Max Activating Token Index: 25

Text #18

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1470. Min Act: -0.0000

Data Index: 340642 (C4 (Web Text))

Max Activating Token Index: 941

Text #19

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1461. Min Act: -0.0000

Data Index: 148112 (C4 (Web Text))

Max Activating Token Index: 681