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

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

Neuron 4651 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0583. Min Act: -0.0001

Data Index: 1562948 (Python Code)

Max Activating Token Index: 137

Text #1

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0566. Min Act: -0.0001

Data Index: 70650 (C4 (Web Text))

Max Activating Token Index: 55

Text #2

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0568. Min Act: -0.0001

Data Index: 773376 (C4 (Web Text))

Max Activating Token Index: 55

Text #3

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0581. Min Act: -0.0001

Data Index: 1545766 (Python Code)

Max Activating Token Index: 519

Text #4

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0563. Min Act: -0.0001

Data Index: 906590 (C4 (Web Text))

Max Activating Token Index: 86

Text #5

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0549. Min Act: -0.0001

Data Index: 481131 (C4 (Web Text))

Max Activating Token Index: 594

Text #6

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0559. Min Act: -0.0001

Data Index: 1527052 (Python Code)

Max Activating Token Index: 644

Text #7

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0507. Min Act: -0.0001

Data Index: 1525861 (Python Code)

Max Activating Token Index: 385

Text #8

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0478. Min Act: -0.0001

Data Index: 1609019 (Python Code)

Max Activating Token Index: 504

Text #9

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0491. Min Act: -0.0001

Data Index: 1136229 (C4 (Web Text))

Max Activating Token Index: 571

Text #10

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0486. Min Act: -0.0001

Data Index: 1553947 (Python Code)

Max Activating Token Index: 276

Text #11

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0479. Min Act: -0.0001

Data Index: 1444407 (Python Code)

Max Activating Token Index: 437

Text #12

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0491. Min Act: -0.0001

Data Index: 56333 (C4 (Web Text))

Max Activating Token Index: 266

Text #13

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0468. Min Act: -0.0001

Data Index: 1636433 (Python Code)

Max Activating Token Index: 161

Text #14

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0459. Min Act: -0.0001

Data Index: 629916 (C4 (Web Text))

Max Activating Token Index: 479

Text #15

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0456. Min Act: -0.0001

Data Index: 48368 (C4 (Web Text))

Max Activating Token Index: 171

Text #16

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0449. Min Act: -0.0001

Data Index: 385570 (C4 (Web Text))

Max Activating Token Index: 50

Text #17

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0470. Min Act: -0.0001

Data Index: 1372657 (Python Code)

Max Activating Token Index: 827

Text #18

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0502. Min Act: -0.0001

Data Index: 622800 (C4 (Web Text))

Max Activating Token Index: 214

Text #19

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0468. Min Act: -0.0001

Data Index: 1424224 (Python Code)

Max Activating Token Index: 627