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

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

Neuron 4130 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: 0.6317. Min Range: -0.6317

Max Act: 0.6317. Min Act: -0.0000

Data Index: 891573 (C4 (Web Text))

Max Activating Token Index: 358

Text #1

Max Range: 0.6317. Min Range: -0.6317

Max Act: 0.4829. Min Act: -0.0000

Data Index: 1534703 (Python Code)

Max Activating Token Index: 244

Text #2

Max Range: 0.6317. Min Range: -0.6317

Max Act: 0.5368. Min Act: -0.0000

Data Index: 887221 (C4 (Web Text))

Max Activating Token Index: 656

Text #3

Max Range: 0.6317. Min Range: -0.6317

Max Act: 0.4627. Min Act: -0.0000

Data Index: 1521478 (Python Code)

Max Activating Token Index: 965

Text #4

Max Range: 0.6317. Min Range: -0.6317

Max Act: 0.4851. Min Act: -0.0000

Data Index: 877591 (C4 (Web Text))

Max Activating Token Index: 601

Text #5

Max Range: 0.6317. Min Range: -0.6317

Max Act: 0.4570. Min Act: -0.0000

Data Index: 1636174 (Python Code)

Max Activating Token Index: 986

Text #6

Max Range: 0.6317. Min Range: -0.6317

Max Act: 0.3811. Min Act: -0.0000

Data Index: 1058652 (C4 (Web Text))

Max Activating Token Index: 876

Text #7

Max Range: 0.6317. Min Range: -0.6317

Max Act: 0.4119. Min Act: -0.0000

Data Index: 168755 (C4 (Web Text))

Max Activating Token Index: 228

Text #8

Max Range: 0.6317. Min Range: -0.6317

Max Act: 0.4010. Min Act: -0.0000

Data Index: 311031 (C4 (Web Text))

Max Activating Token Index: 54

Text #9

Max Range: 0.6317. Min Range: -0.6317

Max Act: 0.3579. Min Act: -0.0000

Data Index: 758885 (C4 (Web Text))

Max Activating Token Index: 944

Text #10

Max Range: 0.6317. Min Range: -0.6317

Max Act: 0.3682. Min Act: -0.0000

Data Index: 1466077 (Python Code)

Max Activating Token Index: 66

Text #11

Max Range: 0.6317. Min Range: -0.6317

Max Act: 0.3633. Min Act: -0.0000

Data Index: 1487419 (Python Code)

Max Activating Token Index: 828

Text #12

Max Range: 0.6317. Min Range: -0.6317

Max Act: 0.3683. Min Act: -0.0000

Data Index: 1518367 (Python Code)

Max Activating Token Index: 830

Text #13

Max Range: 0.6317. Min Range: -0.6317

Max Act: 0.3650. Min Act: -0.0000

Data Index: 1244823 (C4 (Web Text))

Max Activating Token Index: 636

Text #14

Max Range: 0.6317. Min Range: -0.6317

Max Act: 0.3514. Min Act: -0.0000

Data Index: 1466843 (Python Code)

Max Activating Token Index: 828

Text #15

Max Range: 0.6317. Min Range: -0.6317

Max Act: 0.3563. Min Act: -0.0000

Data Index: 659596 (C4 (Web Text))

Max Activating Token Index: 943

Text #16

Max Range: 0.6317. Min Range: -0.6317

Max Act: 0.2999. Min Act: -0.0000

Data Index: 1251061 (C4 (Web Text))

Max Activating Token Index: 726

Text #17

Max Range: 0.6317. Min Range: -0.6317

Max Act: 0.3323. Min Act: -0.0000

Data Index: 170488 (C4 (Web Text))

Max Activating Token Index: 441

Text #18

Max Range: 0.6317. Min Range: -0.6317

Max Act: 0.3489. Min Act: -0.0000

Data Index: 1463582 (Python Code)

Max Activating Token Index: 695

Text #19

Max Range: 0.6317. Min Range: -0.6317

Max Act: 0.3182. Min Act: -0.0000

Data Index: 486467 (C4 (Web Text))

Max Activating Token Index: 553