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

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

Neuron 2034 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2512. Min Range: -0.2512

Max Act: 0.2512. Min Act: -0.0001

Data Index: 767454 (C4 (Web Text))

Max Activating Token Index: 988

Text #1

Max Range: 0.2512. Min Range: -0.2512

Max Act: 0.2395. Min Act: -0.0001

Data Index: 191447 (C4 (Web Text))

Max Activating Token Index: 939

Text #2

Max Range: 0.2512. Min Range: -0.2512

Max Act: 0.2267. Min Act: -0.0001

Data Index: 1333831 (C4 (Web Text))

Max Activating Token Index: 376

Text #3

Max Range: 0.2512. Min Range: -0.2512

Max Act: 0.1969. Min Act: -0.0001

Data Index: 80634 (C4 (Web Text))

Max Activating Token Index: 435

Text #4

Max Range: 0.2512. Min Range: -0.2512

Max Act: 0.2502. Min Act: -0.0001

Data Index: 1248494 (C4 (Web Text))

Max Activating Token Index: 684

Text #5

Max Range: 0.2512. Min Range: -0.2512

Max Act: 0.2232. Min Act: -0.0001

Data Index: 548149 (C4 (Web Text))

Max Activating Token Index: 238

Text #6

Max Range: 0.2512. Min Range: -0.2512

Max Act: 0.2056. Min Act: -0.0001

Data Index: 1124412 (C4 (Web Text))

Max Activating Token Index: 613

Text #7

Max Range: 0.2512. Min Range: -0.2512

Max Act: 0.2113. Min Act: -0.0002

Data Index: 1032965 (C4 (Web Text))

Max Activating Token Index: 562

Text #8

Max Range: 0.2512. Min Range: -0.2512

Max Act: 0.2100. Min Act: -0.0001

Data Index: 684906 (C4 (Web Text))

Max Activating Token Index: 146

Text #9

Max Range: 0.2512. Min Range: -0.2512

Max Act: 0.1896. Min Act: -0.0002

Data Index: 1102034 (C4 (Web Text))

Max Activating Token Index: 737

Text #10

Max Range: 0.2512. Min Range: -0.2512

Max Act: 0.2158. Min Act: -0.0002

Data Index: 924438 (C4 (Web Text))

Max Activating Token Index: 706

Text #11

Max Range: 0.2512. Min Range: -0.2512

Max Act: 0.2073. Min Act: -0.0001

Data Index: 1011897 (C4 (Web Text))

Max Activating Token Index: 213

Text #12

Max Range: 0.2512. Min Range: -0.2512

Max Act: 0.1917. Min Act: -0.0001

Data Index: 926548 (C4 (Web Text))

Max Activating Token Index: 180

Text #13

Max Range: 0.2512. Min Range: -0.2512

Max Act: 0.2002. Min Act: -0.0002

Data Index: 636763 (C4 (Web Text))

Max Activating Token Index: 72

Text #14

Max Range: 0.2512. Min Range: -0.2512

Max Act: 0.1922. Min Act: -0.0001

Data Index: 1060805 (C4 (Web Text))

Max Activating Token Index: 115

Text #15

Max Range: 0.2512. Min Range: -0.2512

Max Act: 0.1747. Min Act: -0.0002

Data Index: 655 (C4 (Web Text))

Max Activating Token Index: 836

Text #16

Max Range: 0.2512. Min Range: -0.2512

Max Act: 0.1777. Min Act: -0.0001

Data Index: 646236 (C4 (Web Text))

Max Activating Token Index: 881

Text #17

Max Range: 0.2512. Min Range: -0.2512

Max Act: 0.1898. Min Act: -0.0002

Data Index: 480983 (C4 (Web Text))

Max Activating Token Index: 765

Text #18

Max Range: 0.2512. Min Range: -0.2512

Max Act: 0.1773. Min Act: -0.0001

Data Index: 928286 (C4 (Web Text))

Max Activating Token Index: 293

Text #19

Max Range: 0.2512. Min Range: -0.2512

Max Act: 0.1799. Min Act: -0.0001

Data Index: 832606 (C4 (Web Text))

Max Activating Token Index: 738