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

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

Neuron 4859 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7611. Min Range: -1.7611

Max Act: 1.7611. Min Act: -0.0000

Data Index: 165873 (C4 (Web Text))

Max Activating Token Index: 55

Text #1

Max Range: 1.7611. Min Range: -1.7611

Max Act: 1.6814. Min Act: -0.0000

Data Index: 578650 (C4 (Web Text))

Max Activating Token Index: 56

Text #2

Max Range: 1.7611. Min Range: -1.7611

Max Act: 1.3988. Min Act: -0.0000

Data Index: 591618 (C4 (Web Text))

Max Activating Token Index: 76

Text #3

Max Range: 1.7611. Min Range: -1.7611

Max Act: 1.3752. Min Act: -0.0000

Data Index: 312142 (C4 (Web Text))

Max Activating Token Index: 880

Text #4

Max Range: 1.7611. Min Range: -1.7611

Max Act: 1.4052. Min Act: -0.0000

Data Index: 783152 (C4 (Web Text))

Max Activating Token Index: 669

Text #5

Max Range: 1.7611. Min Range: -1.7611

Max Act: 1.4575. Min Act: -0.0000

Data Index: 755070 (C4 (Web Text))

Max Activating Token Index: 75

Text #6

Max Range: 1.7611. Min Range: -1.7611

Max Act: 1.4966. Min Act: -0.0000

Data Index: 377321 (C4 (Web Text))

Max Activating Token Index: 517

Text #7

Max Range: 1.7611. Min Range: -1.7611

Max Act: 1.3505. Min Act: -0.0000

Data Index: 1241720 (C4 (Web Text))

Max Activating Token Index: 296

Text #8

Max Range: 1.7611. Min Range: -1.7611

Max Act: 1.4073. Min Act: -0.0000

Data Index: 70737 (C4 (Web Text))

Max Activating Token Index: 522

Text #9

Max Range: 1.7611. Min Range: -1.7611

Max Act: 1.4056. Min Act: -0.0000

Data Index: 1351722 (C4 (Web Text))

Max Activating Token Index: 549

Text #10

Max Range: 1.7611. Min Range: -1.7611

Max Act: 1.3070. Min Act: -0.0000

Data Index: 318647 (C4 (Web Text))

Max Activating Token Index: 937

Text #11

Max Range: 1.7611. Min Range: -1.7611

Max Act: 1.4178. Min Act: -0.0000

Data Index: 459725 (C4 (Web Text))

Max Activating Token Index: 356

Text #12

Max Range: 1.7611. Min Range: -1.7611

Max Act: 1.2883. Min Act: -0.0000

Data Index: 141712 (C4 (Web Text))

Max Activating Token Index: 488

Text #13

Max Range: 1.7611. Min Range: -1.7611

Max Act: 1.4068. Min Act: -0.0000

Data Index: 1609729 (Python Code)

Max Activating Token Index: 804

Text #14

Max Range: 1.7611. Min Range: -1.7611

Max Act: 1.2741. Min Act: -0.0000

Data Index: 232797 (C4 (Web Text))

Max Activating Token Index: 764

Text #15

Max Range: 1.7611. Min Range: -1.7611

Max Act: 1.3444. Min Act: -0.0000

Data Index: 907583 (C4 (Web Text))

Max Activating Token Index: 555

Text #16

Max Range: 1.7611. Min Range: -1.7611

Max Act: 1.3030. Min Act: -0.0000

Data Index: 1174335 (C4 (Web Text))

Max Activating Token Index: 958

Text #17

Max Range: 1.7611. Min Range: -1.7611

Max Act: 1.3774. Min Act: -0.0000

Data Index: 170812 (C4 (Web Text))

Max Activating Token Index: 890

Text #18

Max Range: 1.7611. Min Range: -1.7611

Max Act: 1.3060. Min Act: -0.0000

Data Index: 88218 (C4 (Web Text))

Max Activating Token Index: 105

Text #19

Max Range: 1.7611. Min Range: -1.7611

Max Act: 1.3359. Min Act: -0.0000

Data Index: 391426 (C4 (Web Text))

Max Activating Token Index: 92