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

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

Neuron 2564 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: 0.9687. Min Range: -0.9687

Max Act: 0.9687. Min Act: -0.0001

Data Index: 1014577 (C4 (Web Text))

Max Activating Token Index: 989

Text #1

Max Range: 0.9687. Min Range: -0.9687

Max Act: 0.8594. Min Act: -0.0000

Data Index: 1446682 (Python Code)

Max Activating Token Index: 1004

Text #2

Max Range: 0.9687. Min Range: -0.9687

Max Act: 0.8067. Min Act: -0.0000

Data Index: 1186587 (C4 (Web Text))

Max Activating Token Index: 876

Text #3

Max Range: 0.9687. Min Range: -0.9687

Max Act: 0.8109. Min Act: -0.0000

Data Index: 326160 (C4 (Web Text))

Max Activating Token Index: 161

Text #4

Max Range: 0.9687. Min Range: -0.9687

Max Act: 0.7814. Min Act: -0.0000

Data Index: 1453323 (Python Code)

Max Activating Token Index: 580

Text #5

Max Range: 0.9687. Min Range: -0.9687

Max Act: 0.7642. Min Act: -0.0000

Data Index: 1293340 (C4 (Web Text))

Max Activating Token Index: 487

Text #6

Max Range: 0.9687. Min Range: -0.9687

Max Act: 0.7717. Min Act: -0.0000

Data Index: 1483646 (Python Code)

Max Activating Token Index: 170

Text #7

Max Range: 0.9687. Min Range: -0.9687

Max Act: 0.7367. Min Act: -0.0001

Data Index: 963890 (C4 (Web Text))

Max Activating Token Index: 326

Text #8

Max Range: 0.9687. Min Range: -0.9687

Max Act: 0.6995. Min Act: -0.0000

Data Index: 1340196 (C4 (Web Text))

Max Activating Token Index: 303

Text #9

Max Range: 0.9687. Min Range: -0.9687

Max Act: 0.6952. Min Act: -0.0000

Data Index: 1233446 (C4 (Web Text))

Max Activating Token Index: 440

Text #10

Max Range: 0.9687. Min Range: -0.9687

Max Act: 0.6974. Min Act: -0.0000

Data Index: 678927 (C4 (Web Text))

Max Activating Token Index: 459

Text #11

Max Range: 0.9687. Min Range: -0.9687

Max Act: 0.7503. Min Act: -0.0001

Data Index: 1567218 (Python Code)

Max Activating Token Index: 263

Text #12

Max Range: 0.9687. Min Range: -0.9687

Max Act: 0.7012. Min Act: -0.0000

Data Index: 987933 (C4 (Web Text))

Max Activating Token Index: 114

Text #13

Max Range: 0.9687. Min Range: -0.9687

Max Act: 0.6809. Min Act: -0.0000

Data Index: 1397612 (Python Code)

Max Activating Token Index: 975

Text #14

Max Range: 0.9687. Min Range: -0.9687

Max Act: 0.6379. Min Act: -0.0000

Data Index: 1530651 (Python Code)

Max Activating Token Index: 182

Text #15

Max Range: 0.9687. Min Range: -0.9687

Max Act: 0.7077. Min Act: -0.0000

Data Index: 1405122 (Python Code)

Max Activating Token Index: 123

Text #16

Max Range: 0.9687. Min Range: -0.9687

Max Act: 0.6868. Min Act: -0.0000

Data Index: 1405539 (Python Code)

Max Activating Token Index: 95

Text #17

Max Range: 0.9687. Min Range: -0.9687

Max Act: 0.6983. Min Act: -0.0000

Data Index: 123250 (C4 (Web Text))

Max Activating Token Index: 276

Text #18

Max Range: 0.9687. Min Range: -0.9687

Max Act: 0.6700. Min Act: -0.0000

Data Index: 1431244 (Python Code)

Max Activating Token Index: 636

Text #19

Max Range: 0.9687. Min Range: -0.9687

Max Act: 0.6567. Min Act: -0.0001

Data Index: 779945 (C4 (Web Text))

Max Activating Token Index: 115