Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2697 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3870. Min Range: -0.3870

Max Act: 0.3870. Min Act: -0.0000

Data Index: 846754 (C4 (Web Text))

Max Activating Token Index: 475

Text #1

Max Range: 0.3870. Min Range: -0.3870

Max Act: 0.3307. Min Act: -0.0000

Data Index: 278373 (C4 (Web Text))

Max Activating Token Index: 437

Text #2

Max Range: 0.3870. Min Range: -0.3870

Max Act: 0.3315. Min Act: -0.0000

Data Index: 133237 (C4 (Web Text))

Max Activating Token Index: 157

Text #3

Max Range: 0.3870. Min Range: -0.3870

Max Act: 0.3103. Min Act: -0.0000

Data Index: 103550 (C4 (Web Text))

Max Activating Token Index: 774

Text #4

Max Range: 0.3870. Min Range: -0.3870

Max Act: 0.3035. Min Act: -0.0001

Data Index: 1111911 (C4 (Web Text))

Max Activating Token Index: 831

Text #5

Max Range: 0.3870. Min Range: -0.3870

Max Act: 0.3172. Min Act: -0.0000

Data Index: 374519 (C4 (Web Text))

Max Activating Token Index: 999

Text #6

Max Range: 0.3870. Min Range: -0.3870

Max Act: 0.2886. Min Act: -0.0000

Data Index: 291544 (C4 (Web Text))

Max Activating Token Index: 872

Text #7

Max Range: 0.3870. Min Range: -0.3870

Max Act: 0.2858. Min Act: -0.0000

Data Index: 687650 (C4 (Web Text))

Max Activating Token Index: 1019

Text #8

Max Range: 0.3870. Min Range: -0.3870

Max Act: 0.2866. Min Act: -0.0000

Data Index: 510849 (C4 (Web Text))

Max Activating Token Index: 832

Text #9

Max Range: 0.3870. Min Range: -0.3870

Max Act: 0.2694. Min Act: -0.0001

Data Index: 1170566 (C4 (Web Text))

Max Activating Token Index: 578

Text #10

Max Range: 0.3870. Min Range: -0.3870

Max Act: 0.2770. Min Act: 0.0000

Data Index: 683488 (C4 (Web Text))

Max Activating Token Index: 406

Text #11

Max Range: 0.3870. Min Range: -0.3870

Max Act: 0.2583. Min Act: -0.0001

Data Index: 1337804 (C4 (Web Text))

Max Activating Token Index: 465

Text #12

Max Range: 0.3870. Min Range: -0.3870

Max Act: 0.2701. Min Act: -0.0000

Data Index: 690810 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.3870. Min Range: -0.3870

Max Act: 0.2558. Min Act: -0.0000

Data Index: 303607 (C4 (Web Text))

Max Activating Token Index: 917

Text #14

Max Range: 0.3870. Min Range: -0.3870

Max Act: 0.2652. Min Act: -0.0000

Data Index: 119872 (C4 (Web Text))

Max Activating Token Index: 917

Text #15

Max Range: 0.3870. Min Range: -0.3870

Max Act: 0.2586. Min Act: -0.0000

Data Index: 972230 (C4 (Web Text))

Max Activating Token Index: 179

Text #16

Max Range: 0.3870. Min Range: -0.3870

Max Act: 0.2687. Min Act: -0.0000

Data Index: 307362 (C4 (Web Text))

Max Activating Token Index: 417

Text #17

Max Range: 0.3870. Min Range: -0.3870

Max Act: 0.2684. Min Act: -0.0001

Data Index: 428576 (C4 (Web Text))

Max Activating Token Index: 612

Text #18

Max Range: 0.3870. Min Range: -0.3870

Max Act: 0.2588. Min Act: -0.0000

Data Index: 218618 (C4 (Web Text))

Max Activating Token Index: 450

Text #19

Max Range: 0.3870. Min Range: -0.3870

Max Act: 0.2543. Min Act: -0.0000

Data Index: 501076 (C4 (Web Text))

Max Activating Token Index: 142