Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2161 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.1889. Min Range: -2.1889

Max Act: 2.1338. Min Act: -0.0000

Data Index: 1475219 (Python Code)

Max Activating Token Index: 774

Text #1

Max Range: 2.1889. Min Range: -2.1889

Max Act: 2.1889. Min Act: -0.0001

Data Index: 1188186 (C4 (Web Text))

Max Activating Token Index: 909

Text #2

Max Range: 2.1889. Min Range: -2.1889

Max Act: 2.0924. Min Act: -0.0000

Data Index: 1588891 (Python Code)

Max Activating Token Index: 754

Text #3

Max Range: 2.1889. Min Range: -2.1889

Max Act: 2.1202. Min Act: -0.0000

Data Index: 8579 (C4 (Web Text))

Max Activating Token Index: 758

Text #4

Max Range: 2.1889. Min Range: -2.1889

Max Act: 1.9735. Min Act: -0.0000

Data Index: 1406431 (Python Code)

Max Activating Token Index: 282

Text #5

Max Range: 2.1889. Min Range: -2.1889

Max Act: 1.9789. Min Act: -0.0000

Data Index: 1524084 (Python Code)

Max Activating Token Index: 227

Text #6

Max Range: 2.1889. Min Range: -2.1889

Max Act: 1.9729. Min Act: -0.0001

Data Index: 1651178 (Python Code)

Max Activating Token Index: 691

Text #7

Max Range: 2.1889. Min Range: -2.1889

Max Act: 2.0744. Min Act: -0.0001

Data Index: 1609693 (Python Code)

Max Activating Token Index: 963

Text #8

Max Range: 2.1889. Min Range: -2.1889

Max Act: 2.0314. Min Act: -0.0000

Data Index: 1239782 (C4 (Web Text))

Max Activating Token Index: 235

Text #9

Max Range: 2.1889. Min Range: -2.1889

Max Act: 2.1836. Min Act: -0.0000

Data Index: 1584731 (Python Code)

Max Activating Token Index: 170

Text #10

Max Range: 2.1889. Min Range: -2.1889

Max Act: 1.9244. Min Act: -0.0000

Data Index: 1586094 (Python Code)

Max Activating Token Index: 696

Text #11

Max Range: 2.1889. Min Range: -2.1889

Max Act: 2.1259. Min Act: -0.0000

Data Index: 1570158 (Python Code)

Max Activating Token Index: 848

Text #12

Max Range: 2.1889. Min Range: -2.1889

Max Act: 1.8899. Min Act: -0.0000

Data Index: 1059713 (C4 (Web Text))

Max Activating Token Index: 889

Text #13

Max Range: 2.1889. Min Range: -2.1889

Max Act: 2.1024. Min Act: -0.0000

Data Index: 1483222 (Python Code)

Max Activating Token Index: 658

Text #14

Max Range: 2.1889. Min Range: -2.1889

Max Act: 2.1137. Min Act: -0.0000

Data Index: 1491106 (Python Code)

Max Activating Token Index: 880

Text #15

Max Range: 2.1889. Min Range: -2.1889

Max Act: 1.8970. Min Act: -0.0000

Data Index: 345144 (C4 (Web Text))

Max Activating Token Index: 805

Text #16

Max Range: 2.1889. Min Range: -2.1889

Max Act: 2.0023. Min Act: -0.0000

Data Index: 1590561 (Python Code)

Max Activating Token Index: 951

Text #17

Max Range: 2.1889. Min Range: -2.1889

Max Act: 1.8842. Min Act: -0.0000

Data Index: 1652314 (Python Code)

Max Activating Token Index: 585

Text #18

Max Range: 2.1889. Min Range: -2.1889

Max Act: 2.0613. Min Act: -0.0000

Data Index: 1567176 (Python Code)

Max Activating Token Index: 166

Text #19

Max Range: 2.1889. Min Range: -2.1889

Max Act: 1.9424. Min Act: -0.0000

Data Index: 40893 (C4 (Web Text))

Max Activating Token Index: 18