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

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

Neuron 5355 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3900. Min Range: -0.3900

Max Act: 0.3900. Min Act: -0.0000

Data Index: 619116 (C4 (Web Text))

Max Activating Token Index: 40

Text #1

Max Range: 0.3900. Min Range: -0.3900

Max Act: 0.3537. Min Act: -0.0000

Data Index: 653425 (C4 (Web Text))

Max Activating Token Index: 406

Text #2

Max Range: 0.3900. Min Range: -0.3900

Max Act: 0.3776. Min Act: -0.0000

Data Index: 982545 (C4 (Web Text))

Max Activating Token Index: 417

Text #3

Max Range: 0.3900. Min Range: -0.3900

Max Act: 0.3157. Min Act: -0.0000

Data Index: 653869 (C4 (Web Text))

Max Activating Token Index: 97

Text #4

Max Range: 0.3900. Min Range: -0.3900

Max Act: 0.3043. Min Act: -0.0000

Data Index: 1010562 (C4 (Web Text))

Max Activating Token Index: 318

Text #5

Max Range: 0.3900. Min Range: -0.3900

Max Act: 0.3015. Min Act: -0.0000

Data Index: 1003671 (C4 (Web Text))

Max Activating Token Index: 110

Text #6

Max Range: 0.3900. Min Range: -0.3900

Max Act: 0.2897. Min Act: -0.0000

Data Index: 139282 (C4 (Web Text))

Max Activating Token Index: 518

Text #7

Max Range: 0.3900. Min Range: -0.3900

Max Act: 0.2779. Min Act: -0.0000

Data Index: 558015 (C4 (Web Text))

Max Activating Token Index: 868

Text #8

Max Range: 0.3900. Min Range: -0.3900

Max Act: 0.2739. Min Act: -0.0000

Data Index: 1275583 (C4 (Web Text))

Max Activating Token Index: 630

Text #9

Max Range: 0.3900. Min Range: -0.3900

Max Act: 0.2648. Min Act: -0.0000

Data Index: 935369 (C4 (Web Text))

Max Activating Token Index: 205

Text #10

Max Range: 0.3900. Min Range: -0.3900

Max Act: 0.2643. Min Act: -0.0000

Data Index: 1242564 (C4 (Web Text))

Max Activating Token Index: 719

Text #11

Max Range: 0.3900. Min Range: -0.3900

Max Act: 0.2620. Min Act: -0.0000

Data Index: 1199751 (C4 (Web Text))

Max Activating Token Index: 280

Text #12

Max Range: 0.3900. Min Range: -0.3900

Max Act: 0.2516. Min Act: -0.0000

Data Index: 1197684 (C4 (Web Text))

Max Activating Token Index: 911

Text #13

Max Range: 0.3900. Min Range: -0.3900

Max Act: 0.2524. Min Act: -0.0000

Data Index: 194995 (C4 (Web Text))

Max Activating Token Index: 490

Text #14

Max Range: 0.3900. Min Range: -0.3900

Max Act: 0.2391. Min Act: -0.0000

Data Index: 1108863 (C4 (Web Text))

Max Activating Token Index: 263

Text #15

Max Range: 0.3900. Min Range: -0.3900

Max Act: 0.2554. Min Act: -0.0000

Data Index: 115314 (C4 (Web Text))

Max Activating Token Index: 292

Text #16

Max Range: 0.3900. Min Range: -0.3900

Max Act: 0.2556. Min Act: -0.0000

Data Index: 630057 (C4 (Web Text))

Max Activating Token Index: 588

Text #17

Max Range: 0.3900. Min Range: -0.3900

Max Act: 0.2505. Min Act: -0.0000

Data Index: 725072 (C4 (Web Text))

Max Activating Token Index: 517

Text #18

Max Range: 0.3900. Min Range: -0.3900

Max Act: 0.2427. Min Act: -0.0000

Data Index: 501142 (C4 (Web Text))

Max Activating Token Index: 536

Text #19

Max Range: 0.3900. Min Range: -0.3900

Max Act: 0.2495. Min Act: -0.0000

Data Index: 758617 (C4 (Web Text))

Max Activating Token Index: 396