Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3902 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3141. Min Range: -0.3141

Max Act: 0.3141. Min Act: -0.0000

Data Index: 560945 (C4 (Web Text))

Max Activating Token Index: 322

Text #1

Max Range: 0.3141. Min Range: -0.3141

Max Act: 0.3045. Min Act: -0.0000

Data Index: 909496 (C4 (Web Text))

Max Activating Token Index: 917

Text #2

Max Range: 0.3141. Min Range: -0.3141

Max Act: 0.3049. Min Act: -0.0000

Data Index: 1143253 (C4 (Web Text))

Max Activating Token Index: 69

Text #3

Max Range: 0.3141. Min Range: -0.3141

Max Act: 0.3124. Min Act: -0.0000

Data Index: 435626 (C4 (Web Text))

Max Activating Token Index: 662

Text #4

Max Range: 0.3141. Min Range: -0.3141

Max Act: 0.2929. Min Act: -0.0000

Data Index: 798207 (C4 (Web Text))

Max Activating Token Index: 907

Text #5

Max Range: 0.3141. Min Range: -0.3141

Max Act: 0.2924. Min Act: -0.0000

Data Index: 1043398 (C4 (Web Text))

Max Activating Token Index: 500

Text #6

Max Range: 0.3141. Min Range: -0.3141

Max Act: 0.2889. Min Act: -0.0000

Data Index: 738512 (C4 (Web Text))

Max Activating Token Index: 90

Text #7

Max Range: 0.3141. Min Range: -0.3141

Max Act: 0.2874. Min Act: -0.0000

Data Index: 1257944 (C4 (Web Text))

Max Activating Token Index: 592

Text #8

Max Range: 0.3141. Min Range: -0.3141

Max Act: 0.2850. Min Act: -0.0000

Data Index: 868220 (C4 (Web Text))

Max Activating Token Index: 667

Text #9

Max Range: 0.3141. Min Range: -0.3141

Max Act: 0.2816. Min Act: -0.0000

Data Index: 475811 (C4 (Web Text))

Max Activating Token Index: 672

Text #10

Max Range: 0.3141. Min Range: -0.3141

Max Act: 0.2886. Min Act: -0.0000

Data Index: 430440 (C4 (Web Text))

Max Activating Token Index: 686

Text #11

Max Range: 0.3141. Min Range: -0.3141

Max Act: 0.2703. Min Act: -0.0000

Data Index: 1168087 (C4 (Web Text))

Max Activating Token Index: 757

Text #12

Max Range: 0.3141. Min Range: -0.3141

Max Act: 0.2787. Min Act: -0.0000

Data Index: 540353 (C4 (Web Text))

Max Activating Token Index: 225

Text #13

Max Range: 0.3141. Min Range: -0.3141

Max Act: 0.2696. Min Act: -0.0000

Data Index: 825645 (C4 (Web Text))

Max Activating Token Index: 148

Text #14

Max Range: 0.3141. Min Range: -0.3141

Max Act: 0.2761. Min Act: -0.0000

Data Index: 473118 (C4 (Web Text))

Max Activating Token Index: 51

Text #15

Max Range: 0.3141. Min Range: -0.3141

Max Act: 0.2756. Min Act: -0.0000

Data Index: 480525 (C4 (Web Text))

Max Activating Token Index: 835

Text #16

Max Range: 0.3141. Min Range: -0.3141

Max Act: 0.2700. Min Act: -0.0000

Data Index: 840909 (C4 (Web Text))

Max Activating Token Index: 932

Text #17

Max Range: 0.3141. Min Range: -0.3141

Max Act: 0.2675. Min Act: -0.0000

Data Index: 49938 (C4 (Web Text))

Max Activating Token Index: 124

Text #18

Max Range: 0.3141. Min Range: -0.3141

Max Act: 0.2680. Min Act: -0.0000

Data Index: 1126020 (C4 (Web Text))

Max Activating Token Index: 794

Text #19

Max Range: 0.3141. Min Range: -0.3141

Max Act: 0.2762. Min Act: -0.0000

Data Index: 832908 (C4 (Web Text))

Max Activating Token Index: 689