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

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

Neuron 1277 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6801. Min Range: -2.6801

Max Act: 2.4538. Min Act: -0.0000

Data Index: 833362 (C4 (Web Text))

Max Activating Token Index: 167

Text #1

Max Range: 2.6801. Min Range: -2.6801

Max Act: 2.6801. Min Act: -0.0000

Data Index: 749640 (C4 (Web Text))

Max Activating Token Index: 209

Text #2

Max Range: 2.6801. Min Range: -2.6801

Max Act: 2.2665. Min Act: -0.0000

Data Index: 26038 (C4 (Web Text))

Max Activating Token Index: 755

Text #3

Max Range: 2.6801. Min Range: -2.6801

Max Act: 2.3252. Min Act: -0.0000

Data Index: 635750 (C4 (Web Text))

Max Activating Token Index: 437

Text #4

Max Range: 2.6801. Min Range: -2.6801

Max Act: 2.3926. Min Act: -0.0000

Data Index: 159388 (C4 (Web Text))

Max Activating Token Index: 166

Text #5

Max Range: 2.6801. Min Range: -2.6801

Max Act: 2.4113. Min Act: -0.0000

Data Index: 431408 (C4 (Web Text))

Max Activating Token Index: 273

Text #6

Max Range: 2.6801. Min Range: -2.6801

Max Act: 2.2870. Min Act: -0.0000

Data Index: 676158 (C4 (Web Text))

Max Activating Token Index: 25

Text #7

Max Range: 2.6801. Min Range: -2.6801

Max Act: 2.1329. Min Act: -0.0000

Data Index: 188988 (C4 (Web Text))

Max Activating Token Index: 98

Text #8

Max Range: 2.6801. Min Range: -2.6801

Max Act: 2.3416. Min Act: -0.0000

Data Index: 809945 (C4 (Web Text))

Max Activating Token Index: 37

Text #9

Max Range: 2.6801. Min Range: -2.6801

Max Act: 2.2079. Min Act: -0.0000

Data Index: 686029 (C4 (Web Text))

Max Activating Token Index: 748

Text #10

Max Range: 2.6801. Min Range: -2.6801

Max Act: 2.1102. Min Act: -0.0000

Data Index: 191910 (C4 (Web Text))

Max Activating Token Index: 84

Text #11

Max Range: 2.6801. Min Range: -2.6801

Max Act: 2.1878. Min Act: -0.0000

Data Index: 994615 (C4 (Web Text))

Max Activating Token Index: 207

Text #12

Max Range: 2.6801. Min Range: -2.6801

Max Act: 2.4213. Min Act: -0.0000

Data Index: 199865 (C4 (Web Text))

Max Activating Token Index: 103

Text #13

Max Range: 2.6801. Min Range: -2.6801

Max Act: 2.1438. Min Act: -0.0000

Data Index: 534369 (C4 (Web Text))

Max Activating Token Index: 613

Text #14

Max Range: 2.6801. Min Range: -2.6801

Max Act: 2.2710. Min Act: -0.0000

Data Index: 520437 (C4 (Web Text))

Max Activating Token Index: 758

Text #15

Max Range: 2.6801. Min Range: -2.6801

Max Act: 2.1073. Min Act: -0.0000

Data Index: 816060 (C4 (Web Text))

Max Activating Token Index: 866

Text #16

Max Range: 2.6801. Min Range: -2.6801

Max Act: 1.8089. Min Act: -0.0000

Data Index: 455205 (C4 (Web Text))

Max Activating Token Index: 918

Text #17

Max Range: 2.6801. Min Range: -2.6801

Max Act: 1.9690. Min Act: -0.0000

Data Index: 999162 (C4 (Web Text))

Max Activating Token Index: 392

Text #18

Max Range: 2.6801. Min Range: -2.6801

Max Act: 1.9710. Min Act: -0.0000

Data Index: 180771 (C4 (Web Text))

Max Activating Token Index: 726

Text #19

Max Range: 2.6801. Min Range: -2.6801

Max Act: 1.9315. Min Act: -0.0000

Data Index: 951497 (C4 (Web Text))

Max Activating Token Index: 568