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

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

Neuron 5110 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: 1.2508. Min Range: -1.2508

Max Act: 1.2508. Min Act: 0.0000

Data Index: 1551788 (Python Code)

Max Activating Token Index: 507

Text #1

Max Range: 1.2508. Min Range: -1.2508

Max Act: 1.0309. Min Act: -0.0000

Data Index: 1585108 (Python Code)

Max Activating Token Index: 558

Text #2

Max Range: 1.2508. Min Range: -1.2508

Max Act: 0.9535. Min Act: 0.0000

Data Index: 1424563 (Python Code)

Max Activating Token Index: 592

Text #3

Max Range: 1.2508. Min Range: -1.2508

Max Act: 0.8973. Min Act: -0.0000

Data Index: 129525 (C4 (Web Text))

Max Activating Token Index: 558

Text #4

Max Range: 1.2508. Min Range: -1.2508

Max Act: 0.8417. Min Act: -0.0000

Data Index: 1416425 (Python Code)

Max Activating Token Index: 202

Text #5

Max Range: 1.2508. Min Range: -1.2508

Max Act: 0.8946. Min Act: -0.0000

Data Index: 1610526 (Python Code)

Max Activating Token Index: 786

Text #6

Max Range: 1.2508. Min Range: -1.2508

Max Act: 0.8414. Min Act: 0.0000

Data Index: 1375802 (Python Code)

Max Activating Token Index: 511

Text #7

Max Range: 1.2508. Min Range: -1.2508

Max Act: 0.8151. Min Act: 0.0001

Data Index: 1605203 (Python Code)

Max Activating Token Index: 130

Text #8

Max Range: 1.2508. Min Range: -1.2508

Max Act: 0.7967. Min Act: -0.0000

Data Index: 572640 (C4 (Web Text))

Max Activating Token Index: 616

Text #9

Max Range: 1.2508. Min Range: -1.2508

Max Act: 0.7800. Min Act: 0.0001

Data Index: 1362706 (Python Code)

Max Activating Token Index: 887

Text #10

Max Range: 1.2508. Min Range: -1.2508

Max Act: 0.7694. Min Act: -0.0000

Data Index: 1405420 (Python Code)

Max Activating Token Index: 130

Text #11

Max Range: 1.2508. Min Range: -1.2508

Max Act: 0.7580. Min Act: -0.0000

Data Index: 1487683 (Python Code)

Max Activating Token Index: 208

Text #12

Max Range: 1.2508. Min Range: -1.2508

Max Act: 0.7127. Min Act: -0.0000

Data Index: 1579744 (Python Code)

Max Activating Token Index: 803

Text #13

Max Range: 1.2508. Min Range: -1.2508

Max Act: 0.7481. Min Act: -0.0000

Data Index: 1616226 (Python Code)

Max Activating Token Index: 337

Text #14

Max Range: 1.2508. Min Range: -1.2508

Max Act: 0.7017. Min Act: -0.0000

Data Index: 1525652 (Python Code)

Max Activating Token Index: 1011

Text #15

Max Range: 1.2508. Min Range: -1.2508

Max Act: 0.7115. Min Act: -0.0000

Data Index: 1603557 (Python Code)

Max Activating Token Index: 385

Text #16

Max Range: 1.2508. Min Range: -1.2508

Max Act: 0.6975. Min Act: 0.0001

Data Index: 1500434 (Python Code)

Max Activating Token Index: 312

Text #17

Max Range: 1.2508. Min Range: -1.2508

Max Act: 0.6987. Min Act: -0.0000

Data Index: 1364943 (Python Code)

Max Activating Token Index: 746

Text #18

Max Range: 1.2508. Min Range: -1.2508

Max Act: 0.6955. Min Act: 0.0000

Data Index: 1494752 (Python Code)

Max Activating Token Index: 571

Text #19

Max Range: 1.2508. Min Range: -1.2508

Max Act: 0.6595. Min Act: 0.0000

Data Index: 1392406 (Python Code)

Max Activating Token Index: 573