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

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

Neuron 575 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: 0.6536. Min Range: -0.6536

Max Act: 0.6536. Min Act: -0.0000

Data Index: 1386999 (Python Code)

Max Activating Token Index: 904

Text #1

Max Range: 0.6536. Min Range: -0.6536

Max Act: 0.5822. Min Act: -0.0000

Data Index: 287989 (C4 (Web Text))

Max Activating Token Index: 935

Text #2

Max Range: 0.6536. Min Range: -0.6536

Max Act: 0.5513. Min Act: -0.0000

Data Index: 1580781 (Python Code)

Max Activating Token Index: 719

Text #3

Max Range: 0.6536. Min Range: -0.6536

Max Act: 0.5539. Min Act: -0.0000

Data Index: 1598438 (Python Code)

Max Activating Token Index: 230

Text #4

Max Range: 0.6536. Min Range: -0.6536

Max Act: 0.5089. Min Act: -0.0000

Data Index: 1533001 (Python Code)

Max Activating Token Index: 302

Text #5

Max Range: 0.6536. Min Range: -0.6536

Max Act: 0.5495. Min Act: 0.0000

Data Index: 1402887 (Python Code)

Max Activating Token Index: 535

Text #6

Max Range: 0.6536. Min Range: -0.6536

Max Act: 0.5347. Min Act: -0.0000

Data Index: 1380323 (Python Code)

Max Activating Token Index: 609

Text #7

Max Range: 0.6536. Min Range: -0.6536

Max Act: 0.4960. Min Act: 0.0000

Data Index: 1467467 (Python Code)

Max Activating Token Index: 702

Text #8

Max Range: 0.6536. Min Range: -0.6536

Max Act: 0.4871. Min Act: -0.0000

Data Index: 769823 (C4 (Web Text))

Max Activating Token Index: 707

Text #9

Max Range: 0.6536. Min Range: -0.6536

Max Act: 0.4879. Min Act: -0.0000

Data Index: 1579885 (Python Code)

Max Activating Token Index: 485

Text #10

Max Range: 0.6536. Min Range: -0.6536

Max Act: 0.4962. Min Act: -0.0000

Data Index: 1222609 (C4 (Web Text))

Max Activating Token Index: 740

Text #11

Max Range: 0.6536. Min Range: -0.6536

Max Act: 0.4758. Min Act: -0.0000

Data Index: 911328 (C4 (Web Text))

Max Activating Token Index: 592

Text #12

Max Range: 0.6536. Min Range: -0.6536

Max Act: 0.4437. Min Act: -0.0000

Data Index: 1098353 (C4 (Web Text))

Max Activating Token Index: 487

Text #13

Max Range: 0.6536. Min Range: -0.6536

Max Act: 0.4683. Min Act: -0.0000

Data Index: 1189453 (C4 (Web Text))

Max Activating Token Index: 290

Text #14

Max Range: 0.6536. Min Range: -0.6536

Max Act: 0.4469. Min Act: -0.0000

Data Index: 260978 (C4 (Web Text))

Max Activating Token Index: 432

Text #15

Max Range: 0.6536. Min Range: -0.6536

Max Act: 0.4439. Min Act: 0.0001

Data Index: 1576684 (Python Code)

Max Activating Token Index: 328

Text #16

Max Range: 0.6536. Min Range: -0.6536

Max Act: 0.4600. Min Act: 0.0000

Data Index: 1462168 (Python Code)

Max Activating Token Index: 658

Text #17

Max Range: 0.6536. Min Range: -0.6536

Max Act: 0.4424. Min Act: -0.0000

Data Index: 1636132 (Python Code)

Max Activating Token Index: 420

Text #18

Max Range: 0.6536. Min Range: -0.6536

Max Act: 0.4671. Min Act: -0.0000

Data Index: 803482 (C4 (Web Text))

Max Activating Token Index: 290

Text #19

Max Range: 0.6536. Min Range: -0.6536

Max Act: 0.4550. Min Act: -0.0000

Data Index: 753363 (C4 (Web Text))

Max Activating Token Index: 374