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

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

Neuron 3761 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.7003. Min Act: -0.0001

Data Index: 1181454 (C4 (Web Text))

Max Activating Token Index: 80

Text #1

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.6167. Min Act: -0.0001

Data Index: 1166076 (C4 (Web Text))

Max Activating Token Index: 370

Text #2

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.5432. Min Act: -0.0001

Data Index: 44892 (C4 (Web Text))

Max Activating Token Index: 44

Text #3

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.5339. Min Act: -0.0001

Data Index: 190374 (C4 (Web Text))

Max Activating Token Index: 216

Text #4

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.5581. Min Act: -0.0001

Data Index: 135387 (C4 (Web Text))

Max Activating Token Index: 882

Text #5

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.5155. Min Act: -0.0001

Data Index: 1470214 (Python Code)

Max Activating Token Index: 76

Text #6

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.4611. Min Act: -0.0001

Data Index: 587859 (C4 (Web Text))

Max Activating Token Index: 103

Text #7

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.4630. Min Act: -0.0001

Data Index: 73632 (C4 (Web Text))

Max Activating Token Index: 116

Text #8

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.4816. Min Act: -0.0001

Data Index: 107059 (C4 (Web Text))

Max Activating Token Index: 800

Text #9

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.4826. Min Act: -0.0001

Data Index: 943379 (C4 (Web Text))

Max Activating Token Index: 785

Text #10

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.4485. Min Act: -0.0001

Data Index: 262361 (C4 (Web Text))

Max Activating Token Index: 502

Text #11

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.4683. Min Act: -0.0001

Data Index: 1095060 (C4 (Web Text))

Max Activating Token Index: 14

Text #12

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.4329. Min Act: -0.0001

Data Index: 1318139 (C4 (Web Text))

Max Activating Token Index: 22

Text #13

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.4286. Min Act: -0.0001

Data Index: 566325 (C4 (Web Text))

Max Activating Token Index: 30

Text #14

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.4788. Min Act: -0.0001

Data Index: 1282268 (C4 (Web Text))

Max Activating Token Index: 565

Text #15

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.4629. Min Act: -0.0001

Data Index: 916605 (C4 (Web Text))

Max Activating Token Index: 28

Text #16

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.4165. Min Act: -0.0001

Data Index: 963412 (C4 (Web Text))

Max Activating Token Index: 929

Text #17

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.4113. Min Act: -0.0001

Data Index: 30720 (C4 (Web Text))

Max Activating Token Index: 42

Text #18

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.4184. Min Act: -0.0001

Data Index: 594837 (C4 (Web Text))

Max Activating Token Index: 695

Text #19

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.4182. Min Act: -0.0001

Data Index: 945369 (C4 (Web Text))

Max Activating Token Index: 838