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

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

Neuron 4305 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: 2.4132. Min Range: -2.4132

Max Act: 2.3338. Min Act: -0.0000

Data Index: 1198073 (C4 (Web Text))

Max Activating Token Index: 725

Text #1

Max Range: 2.4132. Min Range: -2.4132

Max Act: 2.3830. Min Act: -0.0000

Data Index: 1352875 (C4 (Web Text))

Max Activating Token Index: 488

Text #2

Max Range: 2.4132. Min Range: -2.4132

Max Act: 2.4132. Min Act: -0.0000

Data Index: 492057 (C4 (Web Text))

Max Activating Token Index: 552

Text #3

Max Range: 2.4132. Min Range: -2.4132

Max Act: 2.3666. Min Act: -0.0000

Data Index: 824932 (C4 (Web Text))

Max Activating Token Index: 214

Text #4

Max Range: 2.4132. Min Range: -2.4132

Max Act: 1.7624. Min Act: -0.0000

Data Index: 1101633 (C4 (Web Text))

Max Activating Token Index: 254

Text #5

Max Range: 2.4132. Min Range: -2.4132

Max Act: 1.6365. Min Act: -0.0000

Data Index: 1154276 (C4 (Web Text))

Max Activating Token Index: 928

Text #6

Max Range: 2.4132. Min Range: -2.4132

Max Act: 1.5809. Min Act: -0.0000

Data Index: 27409 (C4 (Web Text))

Max Activating Token Index: 711

Text #7

Max Range: 2.4132. Min Range: -2.4132

Max Act: 1.5914. Min Act: -0.0000

Data Index: 1034998 (C4 (Web Text))

Max Activating Token Index: 11

Text #8

Max Range: 2.4132. Min Range: -2.4132

Max Act: 1.4745. Min Act: -0.0000

Data Index: 165378 (C4 (Web Text))

Max Activating Token Index: 208

Text #9

Max Range: 2.4132. Min Range: -2.4132

Max Act: 1.4103. Min Act: -0.0000

Data Index: 875366 (C4 (Web Text))

Max Activating Token Index: 82

Text #10

Max Range: 2.4132. Min Range: -2.4132

Max Act: 1.4686. Min Act: -0.0000

Data Index: 907396 (C4 (Web Text))

Max Activating Token Index: 109

Text #11

Max Range: 2.4132. Min Range: -2.4132

Max Act: 1.3317. Min Act: -0.0000

Data Index: 629043 (C4 (Web Text))

Max Activating Token Index: 396

Text #12

Max Range: 2.4132. Min Range: -2.4132

Max Act: 1.1853. Min Act: -0.0000

Data Index: 598580 (C4 (Web Text))

Max Activating Token Index: 853

Text #13

Max Range: 2.4132. Min Range: -2.4132

Max Act: 1.3307. Min Act: -0.0000

Data Index: 226831 (C4 (Web Text))

Max Activating Token Index: 395

Text #14

Max Range: 2.4132. Min Range: -2.4132

Max Act: 1.3488. Min Act: -0.0000

Data Index: 63809 (C4 (Web Text))

Max Activating Token Index: 587

Text #15

Max Range: 2.4132. Min Range: -2.4132

Max Act: 1.3390. Min Act: -0.0000

Data Index: 93788 (C4 (Web Text))

Max Activating Token Index: 580

Text #16

Max Range: 2.4132. Min Range: -2.4132

Max Act: 1.3686. Min Act: -0.0000

Data Index: 843550 (C4 (Web Text))

Max Activating Token Index: 740

Text #17

Max Range: 2.4132. Min Range: -2.4132

Max Act: 1.2951. Min Act: -0.0000

Data Index: 395390 (C4 (Web Text))

Max Activating Token Index: 170

Text #18

Max Range: 2.4132. Min Range: -2.4132

Max Act: 1.2838. Min Act: -0.0000

Data Index: 611696 (C4 (Web Text))

Max Activating Token Index: 608

Text #19

Max Range: 2.4132. Min Range: -2.4132

Max Act: 1.2708. Min Act: -0.0000

Data Index: 110533 (C4 (Web Text))

Max Activating Token Index: 448