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

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

Neuron 3930 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3662. Min Range: -1.3662

Max Act: 1.3662. Min Act: -0.0000

Data Index: 931657 (C4 (Web Text))

Max Activating Token Index: 339

Text #1

Max Range: 1.3662. Min Range: -1.3662

Max Act: 0.8095. Min Act: -0.0000

Data Index: 1012517 (C4 (Web Text))

Max Activating Token Index: 948

Text #2

Max Range: 1.3662. Min Range: -1.3662

Max Act: 0.7124. Min Act: -0.0000

Data Index: 351266 (C4 (Web Text))

Max Activating Token Index: 438

Text #3

Max Range: 1.3662. Min Range: -1.3662

Max Act: 0.6578. Min Act: -0.0000

Data Index: 966578 (C4 (Web Text))

Max Activating Token Index: 508

Text #4

Max Range: 1.3662. Min Range: -1.3662

Max Act: 0.7239. Min Act: -0.0000

Data Index: 1332882 (C4 (Web Text))

Max Activating Token Index: 401

Text #5

Max Range: 1.3662. Min Range: -1.3662

Max Act: 0.6705. Min Act: -0.0000

Data Index: 474942 (C4 (Web Text))

Max Activating Token Index: 906

Text #6

Max Range: 1.3662. Min Range: -1.3662

Max Act: 0.6983. Min Act: -0.0000

Data Index: 1226204 (C4 (Web Text))

Max Activating Token Index: 920

Text #7

Max Range: 1.3662. Min Range: -1.3662

Max Act: 0.6338. Min Act: -0.0000

Data Index: 1237501 (C4 (Web Text))

Max Activating Token Index: 607

Text #8

Max Range: 1.3662. Min Range: -1.3662

Max Act: 0.6184. Min Act: -0.0000

Data Index: 169329 (C4 (Web Text))

Max Activating Token Index: 642

Text #9

Max Range: 1.3662. Min Range: -1.3662

Max Act: 0.6392. Min Act: -0.0000

Data Index: 4989 (C4 (Web Text))

Max Activating Token Index: 148

Text #10

Max Range: 1.3662. Min Range: -1.3662

Max Act: 0.5985. Min Act: -0.0000

Data Index: 1166644 (C4 (Web Text))

Max Activating Token Index: 415

Text #11

Max Range: 1.3662. Min Range: -1.3662

Max Act: 0.5732. Min Act: -0.0000

Data Index: 583653 (C4 (Web Text))

Max Activating Token Index: 966

Text #12

Max Range: 1.3662. Min Range: -1.3662

Max Act: 0.5837. Min Act: -0.0000

Data Index: 1045747 (C4 (Web Text))

Max Activating Token Index: 605

Text #13

Max Range: 1.3662. Min Range: -1.3662

Max Act: 0.5866. Min Act: -0.0000

Data Index: 1325700 (C4 (Web Text))

Max Activating Token Index: 931

Text #14

Max Range: 1.3662. Min Range: -1.3662

Max Act: 0.6112. Min Act: -0.0000

Data Index: 327555 (C4 (Web Text))

Max Activating Token Index: 1011

Text #15

Max Range: 1.3662. Min Range: -1.3662

Max Act: 0.6188. Min Act: -0.0000

Data Index: 328593 (C4 (Web Text))

Max Activating Token Index: 821

Text #16

Max Range: 1.3662. Min Range: -1.3662

Max Act: 0.6021. Min Act: -0.0000

Data Index: 1089386 (C4 (Web Text))

Max Activating Token Index: 720

Text #17

Max Range: 1.3662. Min Range: -1.3662

Max Act: 0.5470. Min Act: -0.0000

Data Index: 618775 (C4 (Web Text))

Max Activating Token Index: 266

Text #18

Max Range: 1.3662. Min Range: -1.3662

Max Act: 0.5882. Min Act: -0.0000

Data Index: 118793 (C4 (Web Text))

Max Activating Token Index: 903

Text #19

Max Range: 1.3662. Min Range: -1.3662

Max Act: 0.6221. Min Act: -0.0000

Data Index: 755042 (C4 (Web Text))

Max Activating Token Index: 203