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

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

Neuron 6023 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5971. Min Range: -2.5971

Max Act: 2.5971. Min Act: -0.0000

Data Index: 694903 (C4 (Web Text))

Max Activating Token Index: 682

Text #1

Max Range: 2.5971. Min Range: -2.5971

Max Act: 2.1833. Min Act: -0.0000

Data Index: 1384424 (Python Code)

Max Activating Token Index: 411

Text #2

Max Range: 2.5971. Min Range: -2.5971

Max Act: 2.2514. Min Act: 0.0000

Data Index: 1473389 (Python Code)

Max Activating Token Index: 661

Text #3

Max Range: 2.5971. Min Range: -2.5971

Max Act: 2.0758. Min Act: 0.0000

Data Index: 1445080 (Python Code)

Max Activating Token Index: 6

Text #4

Max Range: 2.5971. Min Range: -2.5971

Max Act: 2.0205. Min Act: -0.0000

Data Index: 1638947 (Python Code)

Max Activating Token Index: 301

Text #5

Max Range: 2.5971. Min Range: -2.5971

Max Act: 2.0037. Min Act: 0.0000

Data Index: 1532522 (Python Code)

Max Activating Token Index: 683

Text #6

Max Range: 2.5971. Min Range: -2.5971

Max Act: 2.0464. Min Act: -0.0000

Data Index: 1405122 (Python Code)

Max Activating Token Index: 999

Text #7

Max Range: 2.5971. Min Range: -2.5971

Max Act: 1.9385. Min Act: -0.0000

Data Index: 144766 (C4 (Web Text))

Max Activating Token Index: 335

Text #8

Max Range: 2.5971. Min Range: -2.5971

Max Act: 1.8899. Min Act: -0.0000

Data Index: 1608313 (Python Code)

Max Activating Token Index: 514

Text #9

Max Range: 2.5971. Min Range: -2.5971

Max Act: 1.8794. Min Act: -0.0000

Data Index: 1618789 (Python Code)

Max Activating Token Index: 62

Text #10

Max Range: 2.5971. Min Range: -2.5971

Max Act: 1.8761. Min Act: 0.0000

Data Index: 1558463 (Python Code)

Max Activating Token Index: 166

Text #11

Max Range: 2.5971. Min Range: -2.5971

Max Act: 1.8734. Min Act: -0.0000

Data Index: 1437476 (Python Code)

Max Activating Token Index: 132

Text #12

Max Range: 2.5971. Min Range: -2.5971

Max Act: 1.7511. Min Act: 0.0000

Data Index: 1454628 (Python Code)

Max Activating Token Index: 821

Text #13

Max Range: 2.5971. Min Range: -2.5971

Max Act: 1.8589. Min Act: -0.0000

Data Index: 1564318 (Python Code)

Max Activating Token Index: 384

Text #14

Max Range: 2.5971. Min Range: -2.5971

Max Act: 1.8487. Min Act: 0.0000

Data Index: 1520651 (Python Code)

Max Activating Token Index: 218

Text #15

Max Range: 2.5971. Min Range: -2.5971

Max Act: 1.8141. Min Act: -0.0000

Data Index: 1535906 (Python Code)

Max Activating Token Index: 68

Text #16

Max Range: 2.5971. Min Range: -2.5971

Max Act: 1.7928. Min Act: -0.0000

Data Index: 226691 (C4 (Web Text))

Max Activating Token Index: 177

Text #17

Max Range: 2.5971. Min Range: -2.5971

Max Act: 1.8478. Min Act: -0.0000

Data Index: 1370309 (Python Code)

Max Activating Token Index: 438

Text #18

Max Range: 2.5971. Min Range: -2.5971

Max Act: 1.7181. Min Act: -0.0000

Data Index: 1573902 (Python Code)

Max Activating Token Index: 77

Text #19

Max Range: 2.5971. Min Range: -2.5971

Max Act: 1.7026. Min Act: 0.0000

Data Index: 1609990 (Python Code)

Max Activating Token Index: 574