Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3105 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0831. Min Act: -0.0001

Data Index: 155219 (C4 (Web Text))

Max Activating Token Index: 668

Text #1

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0840. Min Act: -0.0001

Data Index: 333659 (C4 (Web Text))

Max Activating Token Index: 227

Text #2

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0669. Min Act: -0.0001

Data Index: 858989 (C4 (Web Text))

Max Activating Token Index: 170

Text #3

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0738. Min Act: -0.0001

Data Index: 633549 (C4 (Web Text))

Max Activating Token Index: 594

Text #4

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0731. Min Act: -0.0001

Data Index: 471631 (C4 (Web Text))

Max Activating Token Index: 474

Text #5

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0721. Min Act: -0.0001

Data Index: 1004460 (C4 (Web Text))

Max Activating Token Index: 246

Text #6

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0690. Min Act: -0.0001

Data Index: 748093 (C4 (Web Text))

Max Activating Token Index: 366

Text #7

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0686. Min Act: -0.0001

Data Index: 594074 (C4 (Web Text))

Max Activating Token Index: 618

Text #8

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0679. Min Act: -0.0001

Data Index: 165119 (C4 (Web Text))

Max Activating Token Index: 465

Text #9

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0707. Min Act: -0.0001

Data Index: 533843 (C4 (Web Text))

Max Activating Token Index: 12

Text #10

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0637. Min Act: -0.0001

Data Index: 1142963 (C4 (Web Text))

Max Activating Token Index: 52

Text #11

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0667. Min Act: -0.0001

Data Index: 605878 (C4 (Web Text))

Max Activating Token Index: 213

Text #12

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0660. Min Act: -0.0000

Data Index: 118174 (C4 (Web Text))

Max Activating Token Index: 383

Text #13

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0635. Min Act: -0.0001

Data Index: 381161 (C4 (Web Text))

Max Activating Token Index: 425

Text #14

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0653. Min Act: -0.0001

Data Index: 1177186 (C4 (Web Text))

Max Activating Token Index: 464

Text #15

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0622. Min Act: -0.0001

Data Index: 686734 (C4 (Web Text))

Max Activating Token Index: 438

Text #16

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0629. Min Act: -0.0001

Data Index: 284546 (C4 (Web Text))

Max Activating Token Index: 219

Text #17

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0625. Min Act: -0.0001

Data Index: 501655 (C4 (Web Text))

Max Activating Token Index: 89

Text #18

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0643. Min Act: -0.0001

Data Index: 780993 (C4 (Web Text))

Max Activating Token Index: 541

Text #19

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0595. Min Act: -0.0001

Data Index: 566170 (C4 (Web Text))

Max Activating Token Index: 31