Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 638 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.7583. Min Range: -0.7583

Max Act: 0.7583. Min Act: -0.0000

Data Index: 354940 (The Pile)

Max Activating Token Index: 930

Text #1

Max Range: 0.7583. Min Range: -0.7583

Max Act: 0.7374. Min Act: -0.0000

Data Index: 388332 (The Pile)

Max Activating Token Index: 278

Text #2

Max Range: 0.7583. Min Range: -0.7583

Max Act: 0.6870. Min Act: -0.0000

Data Index: 160617 (The Pile)

Max Activating Token Index: 215

Text #3

Max Range: 0.7583. Min Range: -0.7583

Max Act: 0.6375. Min Act: -0.0000

Data Index: 883782 (The Pile)

Max Activating Token Index: 676

Text #4

Max Range: 0.7583. Min Range: -0.7583

Max Act: 0.6582. Min Act: -0.0000

Data Index: 655881 (The Pile)

Max Activating Token Index: 495

Text #5

Max Range: 0.7583. Min Range: -0.7583

Max Act: 0.6428. Min Act: -0.0000

Data Index: 135670 (The Pile)

Max Activating Token Index: 192

Text #6

Max Range: 0.7583. Min Range: -0.7583

Max Act: 0.5875. Min Act: -0.0000

Data Index: 997127 (The Pile)

Max Activating Token Index: 307

Text #7

Max Range: 0.7583. Min Range: -0.7583

Max Act: 0.6091. Min Act: -0.0000

Data Index: 1489596 (The Pile)

Max Activating Token Index: 784

Text #8

Max Range: 0.7583. Min Range: -0.7583

Max Act: 0.6250. Min Act: -0.0000

Data Index: 1082576 (The Pile)

Max Activating Token Index: 473

Text #9

Max Range: 0.7583. Min Range: -0.7583

Max Act: 0.6513. Min Act: -0.0001

Data Index: 179200 (The Pile)

Max Activating Token Index: 1001

Text #10

Max Range: 0.7583. Min Range: -0.7583

Max Act: 0.5903. Min Act: -0.0000

Data Index: 1408560 (The Pile)

Max Activating Token Index: 635

Text #11

Max Range: 0.7583. Min Range: -0.7583

Max Act: 0.6032. Min Act: -0.0000

Data Index: 1888890 (The Pile)

Max Activating Token Index: 884

Text #12

Max Range: 0.7583. Min Range: -0.7583

Max Act: 0.6210. Min Act: -0.0000

Data Index: 788167 (The Pile)

Max Activating Token Index: 115

Text #13

Max Range: 0.7583. Min Range: -0.7583

Max Act: 0.6205. Min Act: -0.0000

Data Index: 993302 (The Pile)

Max Activating Token Index: 788

Text #14

Max Range: 0.7583. Min Range: -0.7583

Max Act: 0.6167. Min Act: -0.0000

Data Index: 202288 (The Pile)

Max Activating Token Index: 309

Text #15

Max Range: 0.7583. Min Range: -0.7583

Max Act: 0.5919. Min Act: -0.0000

Data Index: 242724 (The Pile)

Max Activating Token Index: 646

Text #16

Max Range: 0.7583. Min Range: -0.7583

Max Act: 0.5921. Min Act: -0.0000

Data Index: 390924 (The Pile)

Max Activating Token Index: 710

Text #17

Max Range: 0.7583. Min Range: -0.7583

Max Act: 0.5760. Min Act: -0.0000

Data Index: 501356 (The Pile)

Max Activating Token Index: 73

Text #18

Max Range: 0.7583. Min Range: -0.7583

Max Act: 0.5998. Min Act: -0.0000

Data Index: 1416672 (The Pile)

Max Activating Token Index: 314

Text #19

Max Range: 0.7583. Min Range: -0.7583

Max Act: 0.5685. Min Act: -0.0000

Data Index: 1002387 (The Pile)

Max Activating Token Index: 997