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

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

Neuron 2517 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4538. Min Range: -0.4538

Max Act: 0.4538. Min Act: -0.0000

Data Index: 650495 (C4 (Web Text))

Max Activating Token Index: 895

Text #1

Max Range: 0.4538. Min Range: -0.4538

Max Act: 0.4208. Min Act: -0.0000

Data Index: 953210 (C4 (Web Text))

Max Activating Token Index: 536

Text #2

Max Range: 0.4538. Min Range: -0.4538

Max Act: 0.4487. Min Act: -0.0000

Data Index: 148660 (C4 (Web Text))

Max Activating Token Index: 898

Text #3

Max Range: 0.4538. Min Range: -0.4538

Max Act: 0.4102. Min Act: -0.0000

Data Index: 656482 (C4 (Web Text))

Max Activating Token Index: 222

Text #4

Max Range: 0.4538. Min Range: -0.4538

Max Act: 0.3991. Min Act: -0.0000

Data Index: 1583394 (Python Code)

Max Activating Token Index: 66

Text #5

Max Range: 0.4538. Min Range: -0.4538

Max Act: 0.3713. Min Act: -0.0000

Data Index: 360727 (C4 (Web Text))

Max Activating Token Index: 929

Text #6

Max Range: 0.4538. Min Range: -0.4538

Max Act: 0.4038. Min Act: -0.0000

Data Index: 1297407 (C4 (Web Text))

Max Activating Token Index: 938

Text #7

Max Range: 0.4538. Min Range: -0.4538

Max Act: 0.4033. Min Act: -0.0000

Data Index: 681954 (C4 (Web Text))

Max Activating Token Index: 28

Text #8

Max Range: 0.4538. Min Range: -0.4538

Max Act: 0.3838. Min Act: -0.0000

Data Index: 1168170 (C4 (Web Text))

Max Activating Token Index: 592

Text #9

Max Range: 0.4538. Min Range: -0.4538

Max Act: 0.3690. Min Act: -0.0000

Data Index: 1057754 (C4 (Web Text))

Max Activating Token Index: 1008

Text #10

Max Range: 0.4538. Min Range: -0.4538

Max Act: 0.3714. Min Act: -0.0000

Data Index: 243644 (C4 (Web Text))

Max Activating Token Index: 937

Text #11

Max Range: 0.4538. Min Range: -0.4538

Max Act: 0.3794. Min Act: -0.0000

Data Index: 516813 (C4 (Web Text))

Max Activating Token Index: 511

Text #12

Max Range: 0.4538. Min Range: -0.4538

Max Act: 0.3889. Min Act: -0.0000

Data Index: 1644720 (Python Code)

Max Activating Token Index: 507

Text #13

Max Range: 0.4538. Min Range: -0.4538

Max Act: 0.3728. Min Act: -0.0000

Data Index: 272516 (C4 (Web Text))

Max Activating Token Index: 481

Text #14

Max Range: 0.4538. Min Range: -0.4538

Max Act: 0.3687. Min Act: -0.0000

Data Index: 259146 (C4 (Web Text))

Max Activating Token Index: 438

Text #15

Max Range: 0.4538. Min Range: -0.4538

Max Act: 0.3548. Min Act: -0.0000

Data Index: 784244 (C4 (Web Text))

Max Activating Token Index: 922

Text #16

Max Range: 0.4538. Min Range: -0.4538

Max Act: 0.3617. Min Act: -0.0000

Data Index: 196755 (C4 (Web Text))

Max Activating Token Index: 532

Text #17

Max Range: 0.4538. Min Range: -0.4538

Max Act: 0.3838. Min Act: -0.0000

Data Index: 1093576 (C4 (Web Text))

Max Activating Token Index: 155

Text #18

Max Range: 0.4538. Min Range: -0.4538

Max Act: 0.3487. Min Act: -0.0000

Data Index: 176602 (C4 (Web Text))

Max Activating Token Index: 691

Text #19

Max Range: 0.4538. Min Range: -0.4538

Max Act: 0.3606. Min Act: -0.0000

Data Index: 833127 (C4 (Web Text))

Max Activating Token Index: 95