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

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

Neuron 1443 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5434. Min Range: -0.5434

Max Act: 0.5047. Min Act: -0.0000

Data Index: 590022 (C4 (Web Text))

Max Activating Token Index: 620

Text #1

Max Range: 0.5434. Min Range: -0.5434

Max Act: 0.5350. Min Act: -0.0000

Data Index: 268682 (C4 (Web Text))

Max Activating Token Index: 533

Text #2

Max Range: 0.5434. Min Range: -0.5434

Max Act: 0.5434. Min Act: -0.0000

Data Index: 1118400 (C4 (Web Text))

Max Activating Token Index: 60

Text #3

Max Range: 0.5434. Min Range: -0.5434

Max Act: 0.5113. Min Act: -0.0000

Data Index: 1321848 (C4 (Web Text))

Max Activating Token Index: 564

Text #4

Max Range: 0.5434. Min Range: -0.5434

Max Act: 0.4650. Min Act: -0.0000

Data Index: 900130 (C4 (Web Text))

Max Activating Token Index: 919

Text #5

Max Range: 0.5434. Min Range: -0.5434

Max Act: 0.4766. Min Act: -0.0000

Data Index: 397687 (C4 (Web Text))

Max Activating Token Index: 771

Text #6

Max Range: 0.5434. Min Range: -0.5434

Max Act: 0.4647. Min Act: -0.0000

Data Index: 1182505 (C4 (Web Text))

Max Activating Token Index: 527

Text #7

Max Range: 0.5434. Min Range: -0.5434

Max Act: 0.4462. Min Act: -0.0000

Data Index: 51845 (C4 (Web Text))

Max Activating Token Index: 156

Text #8

Max Range: 0.5434. Min Range: -0.5434

Max Act: 0.4350. Min Act: -0.0000

Data Index: 106084 (C4 (Web Text))

Max Activating Token Index: 477

Text #9

Max Range: 0.5434. Min Range: -0.5434

Max Act: 0.4198. Min Act: -0.0000

Data Index: 720340 (C4 (Web Text))

Max Activating Token Index: 266

Text #10

Max Range: 0.5434. Min Range: -0.5434

Max Act: 0.4086. Min Act: -0.0000

Data Index: 1307237 (C4 (Web Text))

Max Activating Token Index: 194

Text #11

Max Range: 0.5434. Min Range: -0.5434

Max Act: 0.3996. Min Act: -0.0000

Data Index: 310195 (C4 (Web Text))

Max Activating Token Index: 755

Text #12

Max Range: 0.5434. Min Range: -0.5434

Max Act: 0.3856. Min Act: -0.0000

Data Index: 83658 (C4 (Web Text))

Max Activating Token Index: 913

Text #13

Max Range: 0.5434. Min Range: -0.5434

Max Act: 0.3769. Min Act: -0.0000

Data Index: 1260587 (C4 (Web Text))

Max Activating Token Index: 282

Text #14

Max Range: 0.5434. Min Range: -0.5434

Max Act: 0.4014. Min Act: -0.0000

Data Index: 1235415 (C4 (Web Text))

Max Activating Token Index: 674

Text #15

Max Range: 0.5434. Min Range: -0.5434

Max Act: 0.4108. Min Act: -0.0000

Data Index: 1083079 (C4 (Web Text))

Max Activating Token Index: 1012

Text #16

Max Range: 0.5434. Min Range: -0.5434

Max Act: 0.4074. Min Act: -0.0000

Data Index: 337525 (C4 (Web Text))

Max Activating Token Index: 780

Text #17

Max Range: 0.5434. Min Range: -0.5434

Max Act: 0.3944. Min Act: -0.0001

Data Index: 535542 (C4 (Web Text))

Max Activating Token Index: 949

Text #18

Max Range: 0.5434. Min Range: -0.5434

Max Act: 0.4124. Min Act: -0.0000

Data Index: 1276085 (C4 (Web Text))

Max Activating Token Index: 630

Text #19

Max Range: 0.5434. Min Range: -0.5434

Max Act: 0.4054. Min Act: -0.0000

Data Index: 1116583 (C4 (Web Text))

Max Activating Token Index: 532