Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 957 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0900. Min Act: -0.0001

Data Index: 1208751 (C4 (Web Text))

Max Activating Token Index: 449

Text #1

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0824. Min Act: -0.0000

Data Index: 579121 (C4 (Web Text))

Max Activating Token Index: 215

Text #2

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0762. Min Act: -0.0000

Data Index: 1289893 (C4 (Web Text))

Max Activating Token Index: 964

Text #3

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0774. Min Act: -0.0000

Data Index: 940448 (C4 (Web Text))

Max Activating Token Index: 197

Text #4

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0682. Min Act: -0.0000

Data Index: 314041 (C4 (Web Text))

Max Activating Token Index: 984

Text #5

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0692. Min Act: -0.0000

Data Index: 73445 (C4 (Web Text))

Max Activating Token Index: 26

Text #6

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0640. Min Act: -0.0001

Data Index: 377414 (C4 (Web Text))

Max Activating Token Index: 263

Text #7

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0637. Min Act: -0.0001

Data Index: 663913 (C4 (Web Text))

Max Activating Token Index: 922

Text #8

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0659. Min Act: -0.0001

Data Index: 251165 (C4 (Web Text))

Max Activating Token Index: 963

Text #9

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0654. Min Act: -0.0000

Data Index: 425690 (C4 (Web Text))

Max Activating Token Index: 550

Text #10

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0677. Min Act: -0.0000

Data Index: 347854 (C4 (Web Text))

Max Activating Token Index: 339

Text #11

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0644. Min Act: -0.0001

Data Index: 469382 (C4 (Web Text))

Max Activating Token Index: 888

Text #12

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0609. Min Act: -0.0000

Data Index: 196285 (C4 (Web Text))

Max Activating Token Index: 647

Text #13

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0633. Min Act: -0.0000

Data Index: 64749 (C4 (Web Text))

Max Activating Token Index: 14

Text #14

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0602. Min Act: -0.0000

Data Index: 215728 (C4 (Web Text))

Max Activating Token Index: 1021

Text #15

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0620. Min Act: -0.0000

Data Index: 767980 (C4 (Web Text))

Max Activating Token Index: 848

Text #16

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0643. Min Act: -0.0000

Data Index: 753056 (C4 (Web Text))

Max Activating Token Index: 819

Text #17

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0597. Min Act: -0.0000

Data Index: 1016015 (C4 (Web Text))

Max Activating Token Index: 131

Text #18

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0640. Min Act: -0.0001

Data Index: 143878 (C4 (Web Text))

Max Activating Token Index: 893

Text #19

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0599. Min Act: -0.0001

Data Index: 916751 (C4 (Web Text))

Max Activating Token Index: 453