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

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

Neuron 3297 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: 1.4547. Min Range: -1.4547

Max Act: 1.4547. Min Act: -0.0000

Data Index: 761031 (C4 (Web Text))

Max Activating Token Index: 143

Text #1

Max Range: 1.4547. Min Range: -1.4547

Max Act: 1.4539. Min Act: -0.0000

Data Index: 637557 (C4 (Web Text))

Max Activating Token Index: 21

Text #2

Max Range: 1.4547. Min Range: -1.4547

Max Act: 1.2756. Min Act: -0.0000

Data Index: 1007041 (C4 (Web Text))

Max Activating Token Index: 801

Text #3

Max Range: 1.4547. Min Range: -1.4547

Max Act: 1.2970. Min Act: -0.0000

Data Index: 1360796 (Python Code)

Max Activating Token Index: 83

Text #4

Max Range: 1.4547. Min Range: -1.4547

Max Act: 1.3676. Min Act: -0.0000

Data Index: 1554829 (Python Code)

Max Activating Token Index: 142

Text #5

Max Range: 1.4547. Min Range: -1.4547

Max Act: 1.2669. Min Act: -0.0000

Data Index: 1389758 (Python Code)

Max Activating Token Index: 78

Text #6

Max Range: 1.4547. Min Range: -1.4547

Max Act: 1.0859. Min Act: -0.0000

Data Index: 1649895 (Python Code)

Max Activating Token Index: 140

Text #7

Max Range: 1.4547. Min Range: -1.4547

Max Act: 1.2141. Min Act: -0.0000

Data Index: 1445921 (Python Code)

Max Activating Token Index: 78

Text #8

Max Range: 1.4547. Min Range: -1.4547

Max Act: 1.2099. Min Act: -0.0000

Data Index: 1384809 (Python Code)

Max Activating Token Index: 50

Text #9

Max Range: 1.4547. Min Range: -1.4547

Max Act: 1.1487. Min Act: -0.0000

Data Index: 1449186 (Python Code)

Max Activating Token Index: 609

Text #10

Max Range: 1.4547. Min Range: -1.4547

Max Act: 1.2026. Min Act: -0.0000

Data Index: 613240 (C4 (Web Text))

Max Activating Token Index: 624

Text #11

Max Range: 1.4547. Min Range: -1.4547

Max Act: 1.1978. Min Act: -0.0000

Data Index: 1632080 (Python Code)

Max Activating Token Index: 468

Text #12

Max Range: 1.4547. Min Range: -1.4547

Max Act: 1.1755. Min Act: -0.0000

Data Index: 582390 (C4 (Web Text))

Max Activating Token Index: 758

Text #13

Max Range: 1.4547. Min Range: -1.4547

Max Act: 1.1528. Min Act: -0.0000

Data Index: 1231729 (C4 (Web Text))

Max Activating Token Index: 474

Text #14

Max Range: 1.4547. Min Range: -1.4547

Max Act: 1.0821. Min Act: -0.0000

Data Index: 1645636 (Python Code)

Max Activating Token Index: 71

Text #15

Max Range: 1.4547. Min Range: -1.4547

Max Act: 1.0766. Min Act: -0.0000

Data Index: 1387691 (Python Code)

Max Activating Token Index: 192

Text #16

Max Range: 1.4547. Min Range: -1.4547

Max Act: 1.1094. Min Act: -0.0000

Data Index: 1446597 (Python Code)

Max Activating Token Index: 541

Text #17

Max Range: 1.4547. Min Range: -1.4547

Max Act: 1.0519. Min Act: -0.0000

Data Index: 1430915 (Python Code)

Max Activating Token Index: 94

Text #18

Max Range: 1.4547. Min Range: -1.4547

Max Act: 1.0157. Min Act: -0.0000

Data Index: 1633653 (Python Code)

Max Activating Token Index: 98

Text #19

Max Range: 1.4547. Min Range: -1.4547

Max Act: 1.1854. Min Act: -0.0000

Data Index: 438114 (C4 (Web Text))

Max Activating Token Index: 323