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

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

Neuron 771 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4826. Min Range: -1.4826

Max Act: 1.4826. Min Act: -0.0000

Data Index: 347683 (C4 (Web Text))

Max Activating Token Index: 767

Text #1

Max Range: 1.4826. Min Range: -1.4826

Max Act: 1.3300. Min Act: -0.0000

Data Index: 695650 (C4 (Web Text))

Max Activating Token Index: 632

Text #2

Max Range: 1.4826. Min Range: -1.4826

Max Act: 1.2816. Min Act: -0.0000

Data Index: 156564 (C4 (Web Text))

Max Activating Token Index: 370

Text #3

Max Range: 1.4826. Min Range: -1.4826

Max Act: 1.0567. Min Act: -0.0000

Data Index: 1032307 (C4 (Web Text))

Max Activating Token Index: 841

Text #4

Max Range: 1.4826. Min Range: -1.4826

Max Act: 0.7761. Min Act: -0.0000

Data Index: 1298360 (C4 (Web Text))

Max Activating Token Index: 372

Text #5

Max Range: 1.4826. Min Range: -1.4826

Max Act: 0.6917. Min Act: -0.0000

Data Index: 160208 (C4 (Web Text))

Max Activating Token Index: 445

Text #6

Max Range: 1.4826. Min Range: -1.4826

Max Act: 0.5847. Min Act: -0.0000

Data Index: 220605 (C4 (Web Text))

Max Activating Token Index: 305

Text #7

Max Range: 1.4826. Min Range: -1.4826

Max Act: 0.5382. Min Act: -0.0000

Data Index: 1108509 (C4 (Web Text))

Max Activating Token Index: 949

Text #8

Max Range: 1.4826. Min Range: -1.4826

Max Act: 0.5415. Min Act: -0.0000

Data Index: 985929 (C4 (Web Text))

Max Activating Token Index: 239

Text #9

Max Range: 1.4826. Min Range: -1.4826

Max Act: 0.4743. Min Act: -0.0000

Data Index: 933189 (C4 (Web Text))

Max Activating Token Index: 708

Text #10

Max Range: 1.4826. Min Range: -1.4826

Max Act: 0.4943. Min Act: -0.0000

Data Index: 695407 (C4 (Web Text))

Max Activating Token Index: 30

Text #11

Max Range: 1.4826. Min Range: -1.4826

Max Act: 0.4483. Min Act: -0.0000

Data Index: 137794 (C4 (Web Text))

Max Activating Token Index: 686

Text #12

Max Range: 1.4826. Min Range: -1.4826

Max Act: 0.4284. Min Act: -0.0000

Data Index: 440535 (C4 (Web Text))

Max Activating Token Index: 302

Text #13

Max Range: 1.4826. Min Range: -1.4826

Max Act: 0.4327. Min Act: -0.0000

Data Index: 377125 (C4 (Web Text))

Max Activating Token Index: 66

Text #14

Max Range: 1.4826. Min Range: -1.4826

Max Act: 0.4520. Min Act: 0.0000

Data Index: 1004110 (C4 (Web Text))

Max Activating Token Index: 871

Text #15

Max Range: 1.4826. Min Range: -1.4826

Max Act: 0.4489. Min Act: -0.0000

Data Index: 774179 (C4 (Web Text))

Max Activating Token Index: 667

Text #16

Max Range: 1.4826. Min Range: -1.4826

Max Act: 0.4240. Min Act: -0.0000

Data Index: 1289080 (C4 (Web Text))

Max Activating Token Index: 465

Text #17

Max Range: 1.4826. Min Range: -1.4826

Max Act: 0.4359. Min Act: -0.0000

Data Index: 922543 (C4 (Web Text))

Max Activating Token Index: 996

Text #18

Max Range: 1.4826. Min Range: -1.4826

Max Act: 0.4069. Min Act: -0.0000

Data Index: 78586 (C4 (Web Text))

Max Activating Token Index: 779

Text #19

Max Range: 1.4826. Min Range: -1.4826

Max Act: 0.4157. Min Act: -0.0000

Data Index: 172226 (C4 (Web Text))

Max Activating Token Index: 335