Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3004 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5871. Min Range: -0.5871

Max Act: 0.5871. Min Act: -0.0000

Data Index: 238826 (C4 (Web Text))

Max Activating Token Index: 637

Text #1

Max Range: 0.5871. Min Range: -0.5871

Max Act: 0.5549. Min Act: -0.0000

Data Index: 852509 (C4 (Web Text))

Max Activating Token Index: 368

Text #2

Max Range: 0.5871. Min Range: -0.5871

Max Act: 0.5770. Min Act: -0.0000

Data Index: 913381 (C4 (Web Text))

Max Activating Token Index: 806

Text #3

Max Range: 0.5871. Min Range: -0.5871

Max Act: 0.5285. Min Act: -0.0000

Data Index: 312941 (C4 (Web Text))

Max Activating Token Index: 947

Text #4

Max Range: 0.5871. Min Range: -0.5871

Max Act: 0.4903. Min Act: -0.0000

Data Index: 713339 (C4 (Web Text))

Max Activating Token Index: 850

Text #5

Max Range: 0.5871. Min Range: -0.5871

Max Act: 0.3932. Min Act: -0.0000

Data Index: 1179792 (C4 (Web Text))

Max Activating Token Index: 1004

Text #6

Max Range: 0.5871. Min Range: -0.5871

Max Act: 0.3920. Min Act: -0.0000

Data Index: 1222200 (C4 (Web Text))

Max Activating Token Index: 936

Text #7

Max Range: 0.5871. Min Range: -0.5871

Max Act: 0.4373. Min Act: -0.0000

Data Index: 712462 (C4 (Web Text))

Max Activating Token Index: 789

Text #8

Max Range: 0.5871. Min Range: -0.5871

Max Act: 0.4370. Min Act: -0.0000

Data Index: 827446 (C4 (Web Text))

Max Activating Token Index: 727

Text #9

Max Range: 0.5871. Min Range: -0.5871

Max Act: 0.4091. Min Act: -0.0000

Data Index: 363460 (C4 (Web Text))

Max Activating Token Index: 366

Text #10

Max Range: 0.5871. Min Range: -0.5871

Max Act: 0.3913. Min Act: -0.0000

Data Index: 333881 (C4 (Web Text))

Max Activating Token Index: 879

Text #11

Max Range: 0.5871. Min Range: -0.5871

Max Act: 0.4412. Min Act: -0.0000

Data Index: 718676 (C4 (Web Text))

Max Activating Token Index: 870

Text #12

Max Range: 0.5871. Min Range: -0.5871

Max Act: 0.3650. Min Act: -0.0000

Data Index: 158506 (C4 (Web Text))

Max Activating Token Index: 382

Text #13

Max Range: 0.5871. Min Range: -0.5871

Max Act: 0.3405. Min Act: -0.0000

Data Index: 752356 (C4 (Web Text))

Max Activating Token Index: 698

Text #14

Max Range: 0.5871. Min Range: -0.5871

Max Act: 0.3762. Min Act: -0.0000

Data Index: 45535 (C4 (Web Text))

Max Activating Token Index: 210

Text #15

Max Range: 0.5871. Min Range: -0.5871

Max Act: 0.3592. Min Act: -0.0000

Data Index: 416377 (C4 (Web Text))

Max Activating Token Index: 47

Text #16

Max Range: 0.5871. Min Range: -0.5871

Max Act: 0.3607. Min Act: -0.0000

Data Index: 1073227 (C4 (Web Text))

Max Activating Token Index: 622

Text #17

Max Range: 0.5871. Min Range: -0.5871

Max Act: 0.3353. Min Act: -0.0000

Data Index: 472672 (C4 (Web Text))

Max Activating Token Index: 634

Text #18

Max Range: 0.5871. Min Range: -0.5871

Max Act: 0.3514. Min Act: -0.0000

Data Index: 1321807 (C4 (Web Text))

Max Activating Token Index: 525

Text #19

Max Range: 0.5871. Min Range: -0.5871

Max Act: 0.3109. Min Act: -0.0000

Data Index: 617074 (C4 (Web Text))

Max Activating Token Index: 752