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

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

Neuron 888 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3378. Min Range: -0.3378

Max Act: 0.3378. Min Act: -0.0001

Data Index: 857411 (C4 (Web Text))

Max Activating Token Index: 824

Text #1

Max Range: 0.3378. Min Range: -0.3378

Max Act: 0.3078. Min Act: -0.0001

Data Index: 407843 (C4 (Web Text))

Max Activating Token Index: 906

Text #2

Max Range: 0.3378. Min Range: -0.3378

Max Act: 0.2885. Min Act: -0.0001

Data Index: 278008 (C4 (Web Text))

Max Activating Token Index: 136

Text #3

Max Range: 0.3378. Min Range: -0.3378

Max Act: 0.2668. Min Act: -0.0001

Data Index: 204321 (C4 (Web Text))

Max Activating Token Index: 546

Text #4

Max Range: 0.3378. Min Range: -0.3378

Max Act: 0.2755. Min Act: -0.0001

Data Index: 545337 (C4 (Web Text))

Max Activating Token Index: 145

Text #5

Max Range: 0.3378. Min Range: -0.3378

Max Act: 0.2888. Min Act: -0.0001

Data Index: 256412 (C4 (Web Text))

Max Activating Token Index: 946

Text #6

Max Range: 0.3378. Min Range: -0.3378

Max Act: 0.2372. Min Act: -0.0001

Data Index: 1079538 (C4 (Web Text))

Max Activating Token Index: 480

Text #7

Max Range: 0.3378. Min Range: -0.3378

Max Act: 0.2263. Min Act: -0.0001

Data Index: 1294629 (C4 (Web Text))

Max Activating Token Index: 954

Text #8

Max Range: 0.3378. Min Range: -0.3378

Max Act: 0.2091. Min Act: -0.0001

Data Index: 440410 (C4 (Web Text))

Max Activating Token Index: 25

Text #9

Max Range: 0.3378. Min Range: -0.3378

Max Act: 0.2143. Min Act: -0.0001

Data Index: 1090810 (C4 (Web Text))

Max Activating Token Index: 836

Text #10

Max Range: 0.3378. Min Range: -0.3378

Max Act: 0.2244. Min Act: -0.0001

Data Index: 932520 (C4 (Web Text))

Max Activating Token Index: 118

Text #11

Max Range: 0.3378. Min Range: -0.3378

Max Act: 0.2141. Min Act: -0.0001

Data Index: 548380 (C4 (Web Text))

Max Activating Token Index: 149

Text #12

Max Range: 0.3378. Min Range: -0.3378

Max Act: 0.1932. Min Act: -0.0001

Data Index: 1355456 (C4 (Web Text))

Max Activating Token Index: 310

Text #13

Max Range: 0.3378. Min Range: -0.3378

Max Act: 0.1911. Min Act: -0.0001

Data Index: 834019 (C4 (Web Text))

Max Activating Token Index: 598

Text #14

Max Range: 0.3378. Min Range: -0.3378

Max Act: 0.1993. Min Act: -0.0001

Data Index: 893349 (C4 (Web Text))

Max Activating Token Index: 713

Text #15

Max Range: 0.3378. Min Range: -0.3378

Max Act: 0.1967. Min Act: -0.0001

Data Index: 930758 (C4 (Web Text))

Max Activating Token Index: 878

Text #16

Max Range: 0.3378. Min Range: -0.3378

Max Act: 0.1898. Min Act: -0.0001

Data Index: 626572 (C4 (Web Text))

Max Activating Token Index: 671

Text #17

Max Range: 0.3378. Min Range: -0.3378

Max Act: 0.1884. Min Act: -0.0001

Data Index: 945727 (C4 (Web Text))

Max Activating Token Index: 106

Text #18

Max Range: 0.3378. Min Range: -0.3378

Max Act: 0.2060. Min Act: -0.0001

Data Index: 454887 (C4 (Web Text))

Max Activating Token Index: 171

Text #19

Max Range: 0.3378. Min Range: -0.3378

Max Act: 0.1958. Min Act: -0.0001

Data Index: 639147 (C4 (Web Text))

Max Activating Token Index: 27