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

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

Neuron 2540 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.3932. Min Act: -0.0001

Data Index: 538841 (C4 (Web Text))

Max Activating Token Index: 235

Text #1

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.3875. Min Act: -0.0001

Data Index: 314757 (C4 (Web Text))

Max Activating Token Index: 177

Text #2

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.3724. Min Act: -0.0001

Data Index: 1335016 (C4 (Web Text))

Max Activating Token Index: 524

Text #3

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.3853. Min Act: -0.0001

Data Index: 669605 (C4 (Web Text))

Max Activating Token Index: 651

Text #4

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.3806. Min Act: -0.0001

Data Index: 374008 (C4 (Web Text))

Max Activating Token Index: 948

Text #5

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.3433. Min Act: -0.0000

Data Index: 121199 (C4 (Web Text))

Max Activating Token Index: 464

Text #6

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.3612. Min Act: -0.0001

Data Index: 171444 (C4 (Web Text))

Max Activating Token Index: 1021

Text #7

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.3408. Min Act: -0.0001

Data Index: 494364 (C4 (Web Text))

Max Activating Token Index: 16

Text #8

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.3252. Min Act: -0.0000

Data Index: 771505 (C4 (Web Text))

Max Activating Token Index: 52

Text #9

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.3127. Min Act: -0.0000

Data Index: 1303660 (C4 (Web Text))

Max Activating Token Index: 475

Text #10

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.3167. Min Act: -0.0001

Data Index: 770372 (C4 (Web Text))

Max Activating Token Index: 709

Text #11

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.2999. Min Act: -0.0000

Data Index: 479472 (C4 (Web Text))

Max Activating Token Index: 169

Text #12

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.3068. Min Act: -0.0000

Data Index: 259828 (C4 (Web Text))

Max Activating Token Index: 559

Text #13

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.3083. Min Act: -0.0000

Data Index: 78154 (C4 (Web Text))

Max Activating Token Index: 620

Text #14

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.2931. Min Act: -0.0001

Data Index: 606585 (C4 (Web Text))

Max Activating Token Index: 684

Text #15

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.3122. Min Act: -0.0001

Data Index: 88596 (C4 (Web Text))

Max Activating Token Index: 510

Text #16

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.2882. Min Act: -0.0001

Data Index: 833848 (C4 (Web Text))

Max Activating Token Index: 243

Text #17

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.2918. Min Act: -0.0001

Data Index: 1195880 (C4 (Web Text))

Max Activating Token Index: 883

Text #18

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.2801. Min Act: -0.0001

Data Index: 711289 (C4 (Web Text))

Max Activating Token Index: 572

Text #19

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.2905. Min Act: -0.0001

Data Index: 1166894 (C4 (Web Text))

Max Activating Token Index: 1011