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

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

Neuron 1611 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.5430. Min Range: -4.5430

Max Act: 4.0267. Min Act: -0.0000

Data Index: 1386577 (Python Code)

Max Activating Token Index: 20

Text #1

Max Range: 4.5430. Min Range: -4.5430

Max Act: 4.5430. Min Act: -0.0000

Data Index: 1481683 (Python Code)

Max Activating Token Index: 21

Text #2

Max Range: 4.5430. Min Range: -4.5430

Max Act: 4.3574. Min Act: -0.0000

Data Index: 1586135 (Python Code)

Max Activating Token Index: 22

Text #3

Max Range: 4.5430. Min Range: -4.5430

Max Act: 3.9689. Min Act: -0.0000

Data Index: 1382910 (Python Code)

Max Activating Token Index: 863

Text #4

Max Range: 4.5430. Min Range: -4.5430

Max Act: 4.1703. Min Act: -0.0000

Data Index: 1588849 (Python Code)

Max Activating Token Index: 71

Text #5

Max Range: 4.5430. Min Range: -4.5430

Max Act: 3.7431. Min Act: -0.0000

Data Index: 1552689 (Python Code)

Max Activating Token Index: 133

Text #6

Max Range: 4.5430. Min Range: -4.5430

Max Act: 3.9034. Min Act: -0.0000

Data Index: 1556894 (Python Code)

Max Activating Token Index: 172

Text #7

Max Range: 4.5430. Min Range: -4.5430

Max Act: 4.3778. Min Act: -0.0000

Data Index: 1461475 (Python Code)

Max Activating Token Index: 148

Text #8

Max Range: 4.5430. Min Range: -4.5430

Max Act: 3.8606. Min Act: -0.0000

Data Index: 1521542 (Python Code)

Max Activating Token Index: 51

Text #9

Max Range: 4.5430. Min Range: -4.5430

Max Act: 3.5439. Min Act: -0.0000

Data Index: 1552129 (Python Code)

Max Activating Token Index: 264

Text #10

Max Range: 4.5430. Min Range: -4.5430

Max Act: 3.7950. Min Act: -0.0000

Data Index: 1465987 (Python Code)

Max Activating Token Index: 154

Text #11

Max Range: 4.5430. Min Range: -4.5430

Max Act: 3.9232. Min Act: -0.0000

Data Index: 1382700 (Python Code)

Max Activating Token Index: 24

Text #12

Max Range: 4.5430. Min Range: -4.5430

Max Act: 3.7653. Min Act: -0.0000

Data Index: 1609571 (Python Code)

Max Activating Token Index: 86

Text #13

Max Range: 4.5430. Min Range: -4.5430

Max Act: 3.2803. Min Act: -0.0000

Data Index: 1602637 (Python Code)

Max Activating Token Index: 123

Text #14

Max Range: 4.5430. Min Range: -4.5430

Max Act: 3.8622. Min Act: -0.0001

Data Index: 1478488 (Python Code)

Max Activating Token Index: 107

Text #15

Max Range: 4.5430. Min Range: -4.5430

Max Act: 3.3340. Min Act: -0.0000

Data Index: 1481369 (Python Code)

Max Activating Token Index: 128

Text #16

Max Range: 4.5430. Min Range: -4.5430

Max Act: 3.4799. Min Act: -0.0000

Data Index: 1345061 (C4 (Web Text))

Max Activating Token Index: 23

Text #17

Max Range: 4.5430. Min Range: -4.5430

Max Act: 3.5131. Min Act: -0.0000

Data Index: 1646712 (Python Code)

Max Activating Token Index: 117

Text #18

Max Range: 4.5430. Min Range: -4.5430

Max Act: 3.6091. Min Act: -0.0000

Data Index: 1480979 (Python Code)

Max Activating Token Index: 51

Text #19

Max Range: 4.5430. Min Range: -4.5430

Max Act: 3.6007. Min Act: -0.0000

Data Index: 1579488 (Python Code)

Max Activating Token Index: 29