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

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

Neuron 2974 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0564. Min Act: -0.0001

Data Index: 296009 (C4 (Web Text))

Max Activating Token Index: 47

Text #1

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0602. Min Act: -0.0001

Data Index: 1625037 (Python Code)

Max Activating Token Index: 563

Text #2

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0603. Min Act: -0.0001

Data Index: 36836 (C4 (Web Text))

Max Activating Token Index: 706

Text #3

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0640. Min Act: -0.0001

Data Index: 67812 (C4 (Web Text))

Max Activating Token Index: 320

Text #4

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0487. Min Act: -0.0001

Data Index: 820367 (C4 (Web Text))

Max Activating Token Index: 208

Text #5

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0568. Min Act: -0.0001

Data Index: 928326 (C4 (Web Text))

Max Activating Token Index: 890

Text #6

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0472. Min Act: -0.0001

Data Index: 914823 (C4 (Web Text))

Max Activating Token Index: 362

Text #7

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0514. Min Act: -0.0001

Data Index: 24615 (C4 (Web Text))

Max Activating Token Index: 603

Text #8

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0510. Min Act: -0.0001

Data Index: 1524938 (Python Code)

Max Activating Token Index: 13

Text #9

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0494. Min Act: -0.0001

Data Index: 1452120 (Python Code)

Max Activating Token Index: 400

Text #10

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0465. Min Act: -0.0001

Data Index: 1563611 (Python Code)

Max Activating Token Index: 358

Text #11

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0472. Min Act: -0.0001

Data Index: 678911 (C4 (Web Text))

Max Activating Token Index: 845

Text #12

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0507. Min Act: -0.0001

Data Index: 204786 (C4 (Web Text))

Max Activating Token Index: 547

Text #13

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0484. Min Act: -0.0001

Data Index: 1408915 (Python Code)

Max Activating Token Index: 10

Text #14

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0464. Min Act: -0.0001

Data Index: 749697 (C4 (Web Text))

Max Activating Token Index: 592

Text #15

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0437. Min Act: -0.0001

Data Index: 1202049 (C4 (Web Text))

Max Activating Token Index: 598

Text #16

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0459. Min Act: -0.0001

Data Index: 478309 (C4 (Web Text))

Max Activating Token Index: 476

Text #17

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0510. Min Act: -0.0001

Data Index: 222157 (C4 (Web Text))

Max Activating Token Index: 18

Text #18

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0405. Min Act: -0.0001

Data Index: 208658 (C4 (Web Text))

Max Activating Token Index: 277

Text #19

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0428. Min Act: -0.0001

Data Index: 544972 (C4 (Web Text))

Max Activating Token Index: 588