Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1801 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0644. Min Act: -0.0002

Data Index: 210558 (C4 (Web Text))

Max Activating Token Index: 579

Text #1

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0648. Min Act: -0.0002

Data Index: 1512864 (Python Code)

Max Activating Token Index: 723

Text #2

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0598. Min Act: -0.0001

Data Index: 663237 (C4 (Web Text))

Max Activating Token Index: 478

Text #3

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0604. Min Act: -0.0002

Data Index: 939265 (C4 (Web Text))

Max Activating Token Index: 751

Text #4

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0592. Min Act: -0.0002

Data Index: 1520849 (Python Code)

Max Activating Token Index: 403

Text #5

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0585. Min Act: -0.0002

Data Index: 1653029 (Python Code)

Max Activating Token Index: 959

Text #6

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0546. Min Act: -0.0002

Data Index: 1379553 (Python Code)

Max Activating Token Index: 916

Text #7

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0519. Min Act: -0.0002

Data Index: 1624168 (Python Code)

Max Activating Token Index: 746

Text #8

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0520. Min Act: -0.0001

Data Index: 1413982 (Python Code)

Max Activating Token Index: 137

Text #9

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0486. Min Act: -0.0002

Data Index: 16075 (C4 (Web Text))

Max Activating Token Index: 402

Text #10

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0496. Min Act: -0.0002

Data Index: 1599902 (Python Code)

Max Activating Token Index: 961

Text #11

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0441. Min Act: -0.0002

Data Index: 1050907 (C4 (Web Text))

Max Activating Token Index: 550

Text #12

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0451. Min Act: -0.0001

Data Index: 1638669 (Python Code)

Max Activating Token Index: 959

Text #13

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0468. Min Act: -0.0002

Data Index: 1634138 (Python Code)

Max Activating Token Index: 476

Text #14

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0481. Min Act: -0.0002

Data Index: 1571195 (Python Code)

Max Activating Token Index: 799

Text #15

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0459. Min Act: -0.0002

Data Index: 1622078 (Python Code)

Max Activating Token Index: 348

Text #16

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0456. Min Act: -0.0002

Data Index: 1502351 (Python Code)

Max Activating Token Index: 523

Text #17

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0451. Min Act: -0.0002

Data Index: 1460952 (Python Code)

Max Activating Token Index: 198

Text #18

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0454. Min Act: -0.0002

Data Index: 807369 (C4 (Web Text))

Max Activating Token Index: 528

Text #19

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0462. Min Act: -0.0002

Data Index: 1511328 (Python Code)

Max Activating Token Index: 261