Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 766 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.5057. Min Range: -0.5057

Max Act: 0.5057. Min Act: -0.0006

Data Index: 155586 (C4 (Web Text))

Max Activating Token Index: 106

Text #1

Max Range: 0.5057. Min Range: -0.5057

Max Act: 0.3863. Min Act: -0.0006

Data Index: 578111 (C4 (Web Text))

Max Activating Token Index: 939

Text #2

Max Range: 0.5057. Min Range: -0.5057

Max Act: 0.3854. Min Act: -0.0006

Data Index: 1214664 (C4 (Web Text))

Max Activating Token Index: 844

Text #3

Max Range: 0.5057. Min Range: -0.5057

Max Act: 0.3680. Min Act: -0.0006

Data Index: 907495 (C4 (Web Text))

Max Activating Token Index: 325

Text #4

Max Range: 0.5057. Min Range: -0.5057

Max Act: 0.3531. Min Act: -0.0006

Data Index: 72064 (C4 (Web Text))

Max Activating Token Index: 874

Text #5

Max Range: 0.5057. Min Range: -0.5057

Max Act: 0.3743. Min Act: -0.0006

Data Index: 1163325 (C4 (Web Text))

Max Activating Token Index: 916

Text #6

Max Range: 0.5057. Min Range: -0.5057

Max Act: 0.3620. Min Act: -0.0006

Data Index: 580874 (C4 (Web Text))

Max Activating Token Index: 767

Text #7

Max Range: 0.5057. Min Range: -0.5057

Max Act: 0.3742. Min Act: -0.0005

Data Index: 773338 (C4 (Web Text))

Max Activating Token Index: 781

Text #8

Max Range: 0.5057. Min Range: -0.5057

Max Act: 0.3719. Min Act: -0.0006

Data Index: 1354096 (C4 (Web Text))

Max Activating Token Index: 519

Text #9

Max Range: 0.5057. Min Range: -0.5057

Max Act: 0.3707. Min Act: -0.0006

Data Index: 375813 (C4 (Web Text))

Max Activating Token Index: 746

Text #10

Max Range: 0.5057. Min Range: -0.5057

Max Act: 0.3693. Min Act: -0.0006

Data Index: 593173 (C4 (Web Text))

Max Activating Token Index: 194

Text #11

Max Range: 0.5057. Min Range: -0.5057

Max Act: 0.3552. Min Act: -0.0006

Data Index: 897809 (C4 (Web Text))

Max Activating Token Index: 741

Text #12

Max Range: 0.5057. Min Range: -0.5057

Max Act: 0.3776. Min Act: -0.0006

Data Index: 1014937 (C4 (Web Text))

Max Activating Token Index: 481

Text #13

Max Range: 0.5057. Min Range: -0.5057

Max Act: 0.3624. Min Act: -0.0006

Data Index: 837712 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.5057. Min Range: -0.5057

Max Act: 0.3512. Min Act: -0.0006

Data Index: 1198248 (C4 (Web Text))

Max Activating Token Index: 834

Text #15

Max Range: 0.5057. Min Range: -0.5057

Max Act: 0.3494. Min Act: -0.0006

Data Index: 626904 (C4 (Web Text))

Max Activating Token Index: 777

Text #16

Max Range: 0.5057. Min Range: -0.5057

Max Act: 0.3599. Min Act: -0.0006

Data Index: 1103457 (C4 (Web Text))

Max Activating Token Index: 797

Text #17

Max Range: 0.5057. Min Range: -0.5057

Max Act: 0.3463. Min Act: -0.0006

Data Index: 908264 (C4 (Web Text))

Max Activating Token Index: 302

Text #18

Max Range: 0.5057. Min Range: -0.5057

Max Act: 0.3461. Min Act: -0.0005

Data Index: 602692 (C4 (Web Text))

Max Activating Token Index: 546

Text #19

Max Range: 0.5057. Min Range: -0.5057

Max Act: 0.3543. Min Act: -0.0006

Data Index: 301972 (C4 (Web Text))

Max Activating Token Index: 290