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

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

Neuron 1782 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4583. Min Range: -0.4583

Max Act: 0.4583. Min Act: -0.0000

Data Index: 734946 (C4 (Web Text))

Max Activating Token Index: 653

Text #1

Max Range: 0.4583. Min Range: -0.4583

Max Act: 0.4551. Min Act: -0.0000

Data Index: 627555 (C4 (Web Text))

Max Activating Token Index: 693

Text #2

Max Range: 0.4583. Min Range: -0.4583

Max Act: 0.4294. Min Act: -0.0001

Data Index: 971630 (C4 (Web Text))

Max Activating Token Index: 268

Text #3

Max Range: 0.4583. Min Range: -0.4583

Max Act: 0.4102. Min Act: -0.0000

Data Index: 41616 (C4 (Web Text))

Max Activating Token Index: 169

Text #4

Max Range: 0.4583. Min Range: -0.4583

Max Act: 0.4058. Min Act: -0.0000

Data Index: 1087911 (C4 (Web Text))

Max Activating Token Index: 795

Text #5

Max Range: 0.4583. Min Range: -0.4583

Max Act: 0.4056. Min Act: -0.0000

Data Index: 11814 (C4 (Web Text))

Max Activating Token Index: 758

Text #6

Max Range: 0.4583. Min Range: -0.4583

Max Act: 0.4062. Min Act: -0.0000

Data Index: 967334 (C4 (Web Text))

Max Activating Token Index: 986

Text #7

Max Range: 0.4583. Min Range: -0.4583

Max Act: 0.3951. Min Act: -0.0000

Data Index: 824860 (C4 (Web Text))

Max Activating Token Index: 630

Text #8

Max Range: 0.4583. Min Range: -0.4583

Max Act: 0.3925. Min Act: -0.0000

Data Index: 84147 (C4 (Web Text))

Max Activating Token Index: 604

Text #9

Max Range: 0.4583. Min Range: -0.4583

Max Act: 0.3967. Min Act: -0.0000

Data Index: 54678 (C4 (Web Text))

Max Activating Token Index: 800

Text #10

Max Range: 0.4583. Min Range: -0.4583

Max Act: 0.3797. Min Act: -0.0000

Data Index: 600726 (C4 (Web Text))

Max Activating Token Index: 272

Text #11

Max Range: 0.4583. Min Range: -0.4583

Max Act: 0.3735. Min Act: -0.0001

Data Index: 1281721 (C4 (Web Text))

Max Activating Token Index: 731

Text #12

Max Range: 0.4583. Min Range: -0.4583

Max Act: 0.3789. Min Act: -0.0000

Data Index: 390828 (C4 (Web Text))

Max Activating Token Index: 550

Text #13

Max Range: 0.4583. Min Range: -0.4583

Max Act: 0.3663. Min Act: -0.0000

Data Index: 1315301 (C4 (Web Text))

Max Activating Token Index: 240

Text #14

Max Range: 0.4583. Min Range: -0.4583

Max Act: 0.3762. Min Act: -0.0001

Data Index: 379530 (C4 (Web Text))

Max Activating Token Index: 832

Text #15

Max Range: 0.4583. Min Range: -0.4583

Max Act: 0.3554. Min Act: -0.0000

Data Index: 1075373 (C4 (Web Text))

Max Activating Token Index: 665

Text #16

Max Range: 0.4583. Min Range: -0.4583

Max Act: 0.3566. Min Act: 0.0000

Data Index: 1186061 (C4 (Web Text))

Max Activating Token Index: 197

Text #17

Max Range: 0.4583. Min Range: -0.4583

Max Act: 0.3589. Min Act: -0.0000

Data Index: 269247 (C4 (Web Text))

Max Activating Token Index: 772

Text #18

Max Range: 0.4583. Min Range: -0.4583

Max Act: 0.3451. Min Act: -0.0001

Data Index: 1044682 (C4 (Web Text))

Max Activating Token Index: 424

Text #19

Max Range: 0.4583. Min Range: -0.4583

Max Act: 0.3537. Min Act: -0.0000

Data Index: 589532 (C4 (Web Text))

Max Activating Token Index: 340