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

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

Neuron 3677 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: 2.0990. Min Range: -2.0990

Max Act: 2.0990. Min Act: -0.0000

Data Index: 1126489 (C4 (Web Text))

Max Activating Token Index: 35

Text #1

Max Range: 2.0990. Min Range: -2.0990

Max Act: 2.0933. Min Act: -0.0000

Data Index: 549785 (C4 (Web Text))

Max Activating Token Index: 66

Text #2

Max Range: 2.0990. Min Range: -2.0990

Max Act: 2.0969. Min Act: -0.0000

Data Index: 1263626 (C4 (Web Text))

Max Activating Token Index: 653

Text #3

Max Range: 2.0990. Min Range: -2.0990

Max Act: 1.7510. Min Act: -0.0000

Data Index: 1168565 (C4 (Web Text))

Max Activating Token Index: 244

Text #4

Max Range: 2.0990. Min Range: -2.0990

Max Act: 1.6921. Min Act: -0.0000

Data Index: 260159 (C4 (Web Text))

Max Activating Token Index: 978

Text #5

Max Range: 2.0990. Min Range: -2.0990

Max Act: 1.5688. Min Act: -0.0000

Data Index: 913764 (C4 (Web Text))

Max Activating Token Index: 183

Text #6

Max Range: 2.0990. Min Range: -2.0990

Max Act: 1.6002. Min Act: -0.0000

Data Index: 590456 (C4 (Web Text))

Max Activating Token Index: 493

Text #7

Max Range: 2.0990. Min Range: -2.0990

Max Act: 1.5975. Min Act: -0.0000

Data Index: 863885 (C4 (Web Text))

Max Activating Token Index: 977

Text #8

Max Range: 2.0990. Min Range: -2.0990

Max Act: 1.5631. Min Act: -0.0000

Data Index: 1299588 (C4 (Web Text))

Max Activating Token Index: 460

Text #9

Max Range: 2.0990. Min Range: -2.0990

Max Act: 1.5616. Min Act: -0.0000

Data Index: 983198 (C4 (Web Text))

Max Activating Token Index: 582

Text #10

Max Range: 2.0990. Min Range: -2.0990

Max Act: 1.5570. Min Act: -0.0000

Data Index: 706585 (C4 (Web Text))

Max Activating Token Index: 741

Text #11

Max Range: 2.0990. Min Range: -2.0990

Max Act: 1.5645. Min Act: -0.0000

Data Index: 1346904 (C4 (Web Text))

Max Activating Token Index: 375

Text #12

Max Range: 2.0990. Min Range: -2.0990

Max Act: 1.5426. Min Act: -0.0000

Data Index: 797486 (C4 (Web Text))

Max Activating Token Index: 504

Text #13

Max Range: 2.0990. Min Range: -2.0990

Max Act: 1.5154. Min Act: -0.0000

Data Index: 162930 (C4 (Web Text))

Max Activating Token Index: 945

Text #14

Max Range: 2.0990. Min Range: -2.0990

Max Act: 1.4581. Min Act: -0.0000

Data Index: 712783 (C4 (Web Text))

Max Activating Token Index: 11

Text #15

Max Range: 2.0990. Min Range: -2.0990

Max Act: 1.4456. Min Act: -0.0000

Data Index: 492496 (C4 (Web Text))

Max Activating Token Index: 987

Text #16

Max Range: 2.0990. Min Range: -2.0990

Max Act: 1.4187. Min Act: -0.0000

Data Index: 1176632 (C4 (Web Text))

Max Activating Token Index: 11

Text #17

Max Range: 2.0990. Min Range: -2.0990

Max Act: 1.5011. Min Act: -0.0000

Data Index: 920522 (C4 (Web Text))

Max Activating Token Index: 975

Text #18

Max Range: 2.0990. Min Range: -2.0990

Max Act: 1.3132. Min Act: -0.0000

Data Index: 1138022 (C4 (Web Text))

Max Activating Token Index: 11

Text #19

Max Range: 2.0990. Min Range: -2.0990

Max Act: 1.3911. Min Act: -0.0000

Data Index: 915045 (C4 (Web Text))

Max Activating Token Index: 600