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

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

Neuron 685 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0992. Min Act: -0.0004

Data Index: 7788 (C4 (Web Text))

Max Activating Token Index: 678

Text #1

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0916. Min Act: -0.0004

Data Index: 165800 (C4 (Web Text))

Max Activating Token Index: 928

Text #2

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0721. Min Act: -0.0004

Data Index: 69917 (C4 (Web Text))

Max Activating Token Index: 630

Text #3

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0929. Min Act: -0.0004

Data Index: 1037454 (C4 (Web Text))

Max Activating Token Index: 895

Text #4

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0851. Min Act: -0.0004

Data Index: 91991 (C4 (Web Text))

Max Activating Token Index: 248

Text #5

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0842. Min Act: -0.0004

Data Index: 322130 (C4 (Web Text))

Max Activating Token Index: 928

Text #6

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0957. Min Act: -0.0004

Data Index: 176791 (C4 (Web Text))

Max Activating Token Index: 299

Text #7

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0878. Min Act: -0.0004

Data Index: 635395 (C4 (Web Text))

Max Activating Token Index: 35

Text #8

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0779. Min Act: -0.0004

Data Index: 645372 (C4 (Web Text))

Max Activating Token Index: 914

Text #9

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0667. Min Act: -0.0004

Data Index: 1228719 (C4 (Web Text))

Max Activating Token Index: 330

Text #10

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0718. Min Act: -0.0004

Data Index: 19922 (C4 (Web Text))

Max Activating Token Index: 642

Text #11

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0693. Min Act: -0.0004

Data Index: 242408 (C4 (Web Text))

Max Activating Token Index: 689

Text #12

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0637. Min Act: -0.0004

Data Index: 822681 (C4 (Web Text))

Max Activating Token Index: 617

Text #13

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0799. Min Act: -0.0004

Data Index: 1109116 (C4 (Web Text))

Max Activating Token Index: 367

Text #14

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0688. Min Act: -0.0004

Data Index: 310567 (C4 (Web Text))

Max Activating Token Index: 839

Text #15

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0743. Min Act: -0.0004

Data Index: 799825 (C4 (Web Text))

Max Activating Token Index: 65

Text #16

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0791. Min Act: -0.0004

Data Index: 302239 (C4 (Web Text))

Max Activating Token Index: 277

Text #17

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0736. Min Act: -0.0004

Data Index: 1295694 (C4 (Web Text))

Max Activating Token Index: 421

Text #18

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0847. Min Act: -0.0004

Data Index: 1204857 (C4 (Web Text))

Max Activating Token Index: 563

Text #19

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0748. Min Act: -0.0004

Data Index: 745599 (C4 (Web Text))

Max Activating Token Index: 274