Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1588 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.1031. Min Act: -0.0003

Data Index: 147787 (C4 (Web Text))

Max Activating Token Index: 134

Text #1

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.1068. Min Act: -0.0003

Data Index: 937202 (C4 (Web Text))

Max Activating Token Index: 497

Text #2

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0990. Min Act: -0.0003

Data Index: 677421 (C4 (Web Text))

Max Activating Token Index: 150

Text #3

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0970. Min Act: -0.0003

Data Index: 72479 (C4 (Web Text))

Max Activating Token Index: 963

Text #4

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0925. Min Act: -0.0003

Data Index: 548958 (C4 (Web Text))

Max Activating Token Index: 32

Text #5

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0892. Min Act: -0.0003

Data Index: 214690 (C4 (Web Text))

Max Activating Token Index: 53

Text #6

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0821. Min Act: -0.0003

Data Index: 383189 (C4 (Web Text))

Max Activating Token Index: 942

Text #7

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0878. Min Act: -0.0003

Data Index: 791434 (C4 (Web Text))

Max Activating Token Index: 22

Text #8

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0890. Min Act: -0.0003

Data Index: 824024 (C4 (Web Text))

Max Activating Token Index: 122

Text #9

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0889. Min Act: -0.0003

Data Index: 123495 (C4 (Web Text))

Max Activating Token Index: 693

Text #10

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0811. Min Act: -0.0004

Data Index: 1154395 (C4 (Web Text))

Max Activating Token Index: 605

Text #11

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0840. Min Act: -0.0003

Data Index: 455352 (C4 (Web Text))

Max Activating Token Index: 343

Text #12

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0798. Min Act: -0.0003

Data Index: 1237102 (C4 (Web Text))

Max Activating Token Index: 674

Text #13

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0825. Min Act: -0.0003

Data Index: 773143 (C4 (Web Text))

Max Activating Token Index: 290

Text #14

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0795. Min Act: -0.0003

Data Index: 438778 (C4 (Web Text))

Max Activating Token Index: 836

Text #15

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0854. Min Act: -0.0003

Data Index: 864522 (C4 (Web Text))

Max Activating Token Index: 382

Text #16

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0820. Min Act: -0.0003

Data Index: 1085411 (C4 (Web Text))

Max Activating Token Index: 415

Text #17

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0821. Min Act: -0.0004

Data Index: 172577 (C4 (Web Text))

Max Activating Token Index: 394

Text #18

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0826. Min Act: -0.0003

Data Index: 1226022 (C4 (Web Text))

Max Activating Token Index: 678

Text #19

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0823. Min Act: -0.0004

Data Index: 295002 (C4 (Web Text))

Max Activating Token Index: 47