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

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

Neuron 2410 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0899. Min Act: -0.0001

Data Index: 282981 (C4 (Web Text))

Max Activating Token Index: 809

Text #1

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0839. Min Act: -0.0001

Data Index: 494725 (C4 (Web Text))

Max Activating Token Index: 323

Text #2

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0864. Min Act: -0.0000

Data Index: 1048080 (C4 (Web Text))

Max Activating Token Index: 77

Text #3

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0851. Min Act: -0.0001

Data Index: 79201 (C4 (Web Text))

Max Activating Token Index: 169

Text #4

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0803. Min Act: -0.0001

Data Index: 1488121 (Python Code)

Max Activating Token Index: 242

Text #5

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0831. Min Act: -0.0001

Data Index: 279714 (C4 (Web Text))

Max Activating Token Index: 674

Text #6

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0770. Min Act: -0.0001

Data Index: 215771 (C4 (Web Text))

Max Activating Token Index: 23

Text #7

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0773. Min Act: -0.0001

Data Index: 736807 (C4 (Web Text))

Max Activating Token Index: 128

Text #8

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0770. Min Act: -0.0001

Data Index: 1653217 (Python Code)

Max Activating Token Index: 23

Text #9

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0784. Min Act: -0.0001

Data Index: 378691 (C4 (Web Text))

Max Activating Token Index: 657

Text #10

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0749. Min Act: -0.0001

Data Index: 1406043 (Python Code)

Max Activating Token Index: 5

Text #11

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0744. Min Act: -0.0001

Data Index: 982062 (C4 (Web Text))

Max Activating Token Index: 18

Text #12

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0752. Min Act: -0.0001

Data Index: 1592375 (Python Code)

Max Activating Token Index: 279

Text #13

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0745. Min Act: -0.0001

Data Index: 205543 (C4 (Web Text))

Max Activating Token Index: 192

Text #14

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0740. Min Act: -0.0001

Data Index: 1577174 (Python Code)

Max Activating Token Index: 539

Text #15

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0739. Min Act: -0.0001

Data Index: 638187 (C4 (Web Text))

Max Activating Token Index: 898

Text #16

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0735. Min Act: -0.0001

Data Index: 1470741 (Python Code)

Max Activating Token Index: 257

Text #17

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0698. Min Act: -0.0001

Data Index: 1490402 (Python Code)

Max Activating Token Index: 366

Text #18

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0701. Min Act: -0.0001

Data Index: 763404 (C4 (Web Text))

Max Activating Token Index: 349

Text #19

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0733. Min Act: -0.0001

Data Index: 551572 (C4 (Web Text))

Max Activating Token Index: 511