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

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

Neuron 2951 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2808. Min Range: -0.2808

Max Act: 0.2621. Min Act: -0.0000

Data Index: 747024 (C4 (Web Text))

Max Activating Token Index: 916

Text #1

Max Range: 0.2808. Min Range: -0.2808

Max Act: 0.2808. Min Act: -0.0001

Data Index: 1422629 (Python Code)

Max Activating Token Index: 946

Text #2

Max Range: 0.2808. Min Range: -0.2808

Max Act: 0.2410. Min Act: -0.0000

Data Index: 1315518 (C4 (Web Text))

Max Activating Token Index: 646

Text #3

Max Range: 0.2808. Min Range: -0.2808

Max Act: 0.2566. Min Act: -0.0000

Data Index: 408270 (C4 (Web Text))

Max Activating Token Index: 123

Text #4

Max Range: 0.2808. Min Range: -0.2808

Max Act: 0.2446. Min Act: -0.0000

Data Index: 1117791 (C4 (Web Text))

Max Activating Token Index: 141

Text #5

Max Range: 0.2808. Min Range: -0.2808

Max Act: 0.2222. Min Act: -0.0000

Data Index: 259552 (C4 (Web Text))

Max Activating Token Index: 157

Text #6

Max Range: 0.2808. Min Range: -0.2808

Max Act: 0.2067. Min Act: -0.0001

Data Index: 741274 (C4 (Web Text))

Max Activating Token Index: 398

Text #7

Max Range: 0.2808. Min Range: -0.2808

Max Act: 0.2116. Min Act: -0.0001

Data Index: 638735 (C4 (Web Text))

Max Activating Token Index: 783

Text #8

Max Range: 0.2808. Min Range: -0.2808

Max Act: 0.2074. Min Act: -0.0000

Data Index: 696880 (C4 (Web Text))

Max Activating Token Index: 890

Text #9

Max Range: 0.2808. Min Range: -0.2808

Max Act: 0.2110. Min Act: -0.0000

Data Index: 818497 (C4 (Web Text))

Max Activating Token Index: 943

Text #10

Max Range: 0.2808. Min Range: -0.2808

Max Act: 0.2013. Min Act: -0.0000

Data Index: 508760 (C4 (Web Text))

Max Activating Token Index: 301

Text #11

Max Range: 0.2808. Min Range: -0.2808

Max Act: 0.2081. Min Act: -0.0000

Data Index: 1248248 (C4 (Web Text))

Max Activating Token Index: 876

Text #12

Max Range: 0.2808. Min Range: -0.2808

Max Act: 0.2061. Min Act: -0.0000

Data Index: 163671 (C4 (Web Text))

Max Activating Token Index: 529

Text #13

Max Range: 0.2808. Min Range: -0.2808

Max Act: 0.1786. Min Act: -0.0001

Data Index: 1201933 (C4 (Web Text))

Max Activating Token Index: 637

Text #14

Max Range: 0.2808. Min Range: -0.2808

Max Act: 0.2031. Min Act: -0.0000

Data Index: 1151345 (C4 (Web Text))

Max Activating Token Index: 422

Text #15

Max Range: 0.2808. Min Range: -0.2808

Max Act: 0.1936. Min Act: -0.0000

Data Index: 756640 (C4 (Web Text))

Max Activating Token Index: 629

Text #16

Max Range: 0.2808. Min Range: -0.2808

Max Act: 0.1811. Min Act: -0.0001

Data Index: 1102772 (C4 (Web Text))

Max Activating Token Index: 165

Text #17

Max Range: 0.2808. Min Range: -0.2808

Max Act: 0.1934. Min Act: -0.0000

Data Index: 287293 (C4 (Web Text))

Max Activating Token Index: 995

Text #18

Max Range: 0.2808. Min Range: -0.2808

Max Act: 0.1927. Min Act: -0.0001

Data Index: 808555 (C4 (Web Text))

Max Activating Token Index: 1019

Text #19

Max Range: 0.2808. Min Range: -0.2808

Max Act: 0.1844. Min Act: -0.0000

Data Index: 651661 (C4 (Web Text))

Max Activating Token Index: 58