Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2210 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.2370. Min Act: -0.0001

Data Index: 403040 (C4 (Web Text))

Max Activating Token Index: 614

Text #1

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.2155. Min Act: -0.0001

Data Index: 1074442 (C4 (Web Text))

Max Activating Token Index: 914

Text #2

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.2053. Min Act: -0.0001

Data Index: 154224 (C4 (Web Text))

Max Activating Token Index: 355

Text #3

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.2003. Min Act: -0.0001

Data Index: 244598 (C4 (Web Text))

Max Activating Token Index: 487

Text #4

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1910. Min Act: -0.0001

Data Index: 590944 (C4 (Web Text))

Max Activating Token Index: 403

Text #5

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1948. Min Act: -0.0001

Data Index: 57464 (C4 (Web Text))

Max Activating Token Index: 261

Text #6

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1883. Min Act: -0.0001

Data Index: 1244300 (C4 (Web Text))

Max Activating Token Index: 669

Text #7

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1853. Min Act: -0.0001

Data Index: 906075 (C4 (Web Text))

Max Activating Token Index: 33

Text #8

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1894. Min Act: -0.0000

Data Index: 455314 (C4 (Web Text))

Max Activating Token Index: 105

Text #9

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1825. Min Act: -0.0001

Data Index: 283015 (C4 (Web Text))

Max Activating Token Index: 639

Text #10

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1770. Min Act: -0.0001

Data Index: 546503 (C4 (Web Text))

Max Activating Token Index: 229

Text #11

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1751. Min Act: -0.0001

Data Index: 901042 (C4 (Web Text))

Max Activating Token Index: 842

Text #12

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1857. Min Act: -0.0001

Data Index: 579657 (C4 (Web Text))

Max Activating Token Index: 48

Text #13

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1603. Min Act: -0.0001

Data Index: 171647 (C4 (Web Text))

Max Activating Token Index: 890

Text #14

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1684. Min Act: -0.0001

Data Index: 1048396 (C4 (Web Text))

Max Activating Token Index: 410

Text #15

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1677. Min Act: -0.0001

Data Index: 494416 (C4 (Web Text))

Max Activating Token Index: 433

Text #16

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1645. Min Act: -0.0000

Data Index: 108079 (C4 (Web Text))

Max Activating Token Index: 303

Text #17

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1614. Min Act: -0.0000

Data Index: 171082 (C4 (Web Text))

Max Activating Token Index: 608

Text #18

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1618. Min Act: -0.0001

Data Index: 389701 (C4 (Web Text))

Max Activating Token Index: 309

Text #19

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1686. Min Act: -0.0000

Data Index: 164774 (C4 (Web Text))

Max Activating Token Index: 660