Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4128 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.8154. Min Range: -0.8154

Max Act: 0.8154. Min Act: -0.0000

Data Index: 110779 (C4 (Web Text))

Max Activating Token Index: 259

Text #1

Max Range: 0.8154. Min Range: -0.8154

Max Act: 0.7445. Min Act: 0.0000

Data Index: 1130386 (C4 (Web Text))

Max Activating Token Index: 881

Text #2

Max Range: 0.8154. Min Range: -0.8154

Max Act: 0.5734. Min Act: -0.0000

Data Index: 178977 (C4 (Web Text))

Max Activating Token Index: 837

Text #3

Max Range: 0.8154. Min Range: -0.8154

Max Act: 0.5810. Min Act: -0.0000

Data Index: 934804 (C4 (Web Text))

Max Activating Token Index: 518

Text #4

Max Range: 0.8154. Min Range: -0.8154

Max Act: 0.5812. Min Act: -0.0000

Data Index: 67873 (C4 (Web Text))

Max Activating Token Index: 992

Text #5

Max Range: 0.8154. Min Range: -0.8154

Max Act: 0.5637. Min Act: -0.0000

Data Index: 1021875 (C4 (Web Text))

Max Activating Token Index: 311

Text #6

Max Range: 0.8154. Min Range: -0.8154

Max Act: 0.5442. Min Act: -0.0000

Data Index: 171508 (C4 (Web Text))

Max Activating Token Index: 419

Text #7

Max Range: 0.8154. Min Range: -0.8154

Max Act: 0.5112. Min Act: -0.0000

Data Index: 747664 (C4 (Web Text))

Max Activating Token Index: 323

Text #8

Max Range: 0.8154. Min Range: -0.8154

Max Act: 0.4868. Min Act: -0.0000

Data Index: 897720 (C4 (Web Text))

Max Activating Token Index: 433

Text #9

Max Range: 0.8154. Min Range: -0.8154

Max Act: 0.4794. Min Act: 0.0000

Data Index: 83774 (C4 (Web Text))

Max Activating Token Index: 436

Text #10

Max Range: 0.8154. Min Range: -0.8154

Max Act: 0.4992. Min Act: -0.0000

Data Index: 110569 (C4 (Web Text))

Max Activating Token Index: 905

Text #11

Max Range: 0.8154. Min Range: -0.8154

Max Act: 0.5075. Min Act: -0.0000

Data Index: 437403 (C4 (Web Text))

Max Activating Token Index: 256

Text #12

Max Range: 0.8154. Min Range: -0.8154

Max Act: 0.4707. Min Act: -0.0000

Data Index: 1253692 (C4 (Web Text))

Max Activating Token Index: 594

Text #13

Max Range: 0.8154. Min Range: -0.8154

Max Act: 0.4674. Min Act: -0.0000

Data Index: 226584 (C4 (Web Text))

Max Activating Token Index: 639

Text #14

Max Range: 0.8154. Min Range: -0.8154

Max Act: 0.4788. Min Act: 0.0000

Data Index: 418265 (C4 (Web Text))

Max Activating Token Index: 594

Text #15

Max Range: 0.8154. Min Range: -0.8154

Max Act: 0.5073. Min Act: -0.0000

Data Index: 29926 (C4 (Web Text))

Max Activating Token Index: 752

Text #16

Max Range: 0.8154. Min Range: -0.8154

Max Act: 0.4679. Min Act: -0.0000

Data Index: 755022 (C4 (Web Text))

Max Activating Token Index: 874

Text #17

Max Range: 0.8154. Min Range: -0.8154

Max Act: 0.5014. Min Act: -0.0000

Data Index: 71992 (C4 (Web Text))

Max Activating Token Index: 641

Text #18

Max Range: 0.8154. Min Range: -0.8154

Max Act: 0.4668. Min Act: 0.0001

Data Index: 48959 (C4 (Web Text))

Max Activating Token Index: 935

Text #19

Max Range: 0.8154. Min Range: -0.8154

Max Act: 0.4786. Min Act: -0.0000

Data Index: 946036 (C4 (Web Text))

Max Activating Token Index: 876