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

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

Neuron 3026 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5825. Min Range: -0.5825

Max Act: 0.5825. Min Act: -0.0000

Data Index: 281350 (C4 (Web Text))

Max Activating Token Index: 853

Text #1

Max Range: 0.5825. Min Range: -0.5825

Max Act: 0.4741. Min Act: -0.0000

Data Index: 42343 (C4 (Web Text))

Max Activating Token Index: 765

Text #2

Max Range: 0.5825. Min Range: -0.5825

Max Act: 0.5218. Min Act: -0.0000

Data Index: 314987 (C4 (Web Text))

Max Activating Token Index: 254

Text #3

Max Range: 0.5825. Min Range: -0.5825

Max Act: 0.5014. Min Act: -0.0000

Data Index: 619274 (C4 (Web Text))

Max Activating Token Index: 558

Text #4

Max Range: 0.5825. Min Range: -0.5825

Max Act: 0.4998. Min Act: -0.0000

Data Index: 33077 (C4 (Web Text))

Max Activating Token Index: 138

Text #5

Max Range: 0.5825. Min Range: -0.5825

Max Act: 0.4929. Min Act: -0.0000

Data Index: 1184006 (C4 (Web Text))

Max Activating Token Index: 525

Text #6

Max Range: 0.5825. Min Range: -0.5825

Max Act: 0.5081. Min Act: -0.0000

Data Index: 126051 (C4 (Web Text))

Max Activating Token Index: 342

Text #7

Max Range: 0.5825. Min Range: -0.5825

Max Act: 0.4853. Min Act: -0.0000

Data Index: 1022568 (C4 (Web Text))

Max Activating Token Index: 956

Text #8

Max Range: 0.5825. Min Range: -0.5825

Max Act: 0.4732. Min Act: -0.0000

Data Index: 1202003 (C4 (Web Text))

Max Activating Token Index: 564

Text #9

Max Range: 0.5825. Min Range: -0.5825

Max Act: 0.4920. Min Act: -0.0000

Data Index: 666434 (C4 (Web Text))

Max Activating Token Index: 503

Text #10

Max Range: 0.5825. Min Range: -0.5825

Max Act: 0.4742. Min Act: -0.0000

Data Index: 886155 (C4 (Web Text))

Max Activating Token Index: 508

Text #11

Max Range: 0.5825. Min Range: -0.5825

Max Act: 0.4856. Min Act: -0.0000

Data Index: 581040 (C4 (Web Text))

Max Activating Token Index: 82

Text #12

Max Range: 0.5825. Min Range: -0.5825

Max Act: 0.4716. Min Act: -0.0000

Data Index: 1133455 (C4 (Web Text))

Max Activating Token Index: 161

Text #13

Max Range: 0.5825. Min Range: -0.5825

Max Act: 0.4560. Min Act: -0.0000

Data Index: 1015071 (C4 (Web Text))

Max Activating Token Index: 489

Text #14

Max Range: 0.5825. Min Range: -0.5825

Max Act: 0.4788. Min Act: -0.0000

Data Index: 371737 (C4 (Web Text))

Max Activating Token Index: 354

Text #15

Max Range: 0.5825. Min Range: -0.5825

Max Act: 0.4612. Min Act: -0.0000

Data Index: 1221617 (C4 (Web Text))

Max Activating Token Index: 498

Text #16

Max Range: 0.5825. Min Range: -0.5825

Max Act: 0.4712. Min Act: -0.0000

Data Index: 396198 (C4 (Web Text))

Max Activating Token Index: 687

Text #17

Max Range: 0.5825. Min Range: -0.5825

Max Act: 0.4539. Min Act: -0.0000

Data Index: 360677 (C4 (Web Text))

Max Activating Token Index: 611

Text #18

Max Range: 0.5825. Min Range: -0.5825

Max Act: 0.4699. Min Act: -0.0000

Data Index: 112868 (C4 (Web Text))

Max Activating Token Index: 512

Text #19

Max Range: 0.5825. Min Range: -0.5825

Max Act: 0.4436. Min Act: -0.0000

Data Index: 25439 (C4 (Web Text))

Max Activating Token Index: 869