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

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

Neuron 4130 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5035. Min Range: -0.5035

Max Act: 0.5035. Min Act: -0.0000

Data Index: 400687 (C4 (Web Text))

Max Activating Token Index: 651

Text #1

Max Range: 0.5035. Min Range: -0.5035

Max Act: 0.4646. Min Act: -0.0000

Data Index: 574427 (C4 (Web Text))

Max Activating Token Index: 490

Text #2

Max Range: 0.5035. Min Range: -0.5035

Max Act: 0.4655. Min Act: -0.0000

Data Index: 225678 (C4 (Web Text))

Max Activating Token Index: 707

Text #3

Max Range: 0.5035. Min Range: -0.5035

Max Act: 0.4531. Min Act: -0.0000

Data Index: 659931 (C4 (Web Text))

Max Activating Token Index: 393

Text #4

Max Range: 0.5035. Min Range: -0.5035

Max Act: 0.4342. Min Act: -0.0000

Data Index: 355438 (C4 (Web Text))

Max Activating Token Index: 378

Text #5

Max Range: 0.5035. Min Range: -0.5035

Max Act: 0.4297. Min Act: -0.0000

Data Index: 847726 (C4 (Web Text))

Max Activating Token Index: 771

Text #6

Max Range: 0.5035. Min Range: -0.5035

Max Act: 0.4012. Min Act: -0.0000

Data Index: 1156306 (C4 (Web Text))

Max Activating Token Index: 635

Text #7

Max Range: 0.5035. Min Range: -0.5035

Max Act: 0.4201. Min Act: -0.0000

Data Index: 21340 (C4 (Web Text))

Max Activating Token Index: 911

Text #8

Max Range: 0.5035. Min Range: -0.5035

Max Act: 0.4060. Min Act: -0.0000

Data Index: 1255283 (C4 (Web Text))

Max Activating Token Index: 919

Text #9

Max Range: 0.5035. Min Range: -0.5035

Max Act: 0.4022. Min Act: -0.0000

Data Index: 1284444 (C4 (Web Text))

Max Activating Token Index: 849

Text #10

Max Range: 0.5035. Min Range: -0.5035

Max Act: 0.3970. Min Act: -0.0000

Data Index: 740921 (C4 (Web Text))

Max Activating Token Index: 286

Text #11

Max Range: 0.5035. Min Range: -0.5035

Max Act: 0.3968. Min Act: -0.0000

Data Index: 902165 (C4 (Web Text))

Max Activating Token Index: 159

Text #12

Max Range: 0.5035. Min Range: -0.5035

Max Act: 0.4221. Min Act: -0.0000

Data Index: 623456 (C4 (Web Text))

Max Activating Token Index: 637

Text #13

Max Range: 0.5035. Min Range: -0.5035

Max Act: 0.3945. Min Act: 0.0001

Data Index: 862539 (C4 (Web Text))

Max Activating Token Index: 198

Text #14

Max Range: 0.5035. Min Range: -0.5035

Max Act: 0.3957. Min Act: -0.0000

Data Index: 576055 (C4 (Web Text))

Max Activating Token Index: 824

Text #15

Max Range: 0.5035. Min Range: -0.5035

Max Act: 0.3718. Min Act: -0.0000

Data Index: 1353037 (C4 (Web Text))

Max Activating Token Index: 127

Text #16

Max Range: 0.5035. Min Range: -0.5035

Max Act: 0.3738. Min Act: 0.0000

Data Index: 518706 (C4 (Web Text))

Max Activating Token Index: 18

Text #17

Max Range: 0.5035. Min Range: -0.5035

Max Act: 0.3799. Min Act: -0.0000

Data Index: 230497 (C4 (Web Text))

Max Activating Token Index: 1005

Text #18

Max Range: 0.5035. Min Range: -0.5035

Max Act: 0.3561. Min Act: -0.0000

Data Index: 1308659 (C4 (Web Text))

Max Activating Token Index: 44

Text #19

Max Range: 0.5035. Min Range: -0.5035

Max Act: 0.3593. Min Act: 0.0000

Data Index: 263081 (C4 (Web Text))

Max Activating Token Index: 278