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

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

Neuron 2869 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5914. Min Range: -1.5914

Max Act: 1.5914. Min Act: -0.0000

Data Index: 211961 (C4 (Web Text))

Max Activating Token Index: 989

Text #1

Max Range: 1.5914. Min Range: -1.5914

Max Act: 1.5588. Min Act: -0.0001

Data Index: 272633 (C4 (Web Text))

Max Activating Token Index: 356

Text #2

Max Range: 1.5914. Min Range: -1.5914

Max Act: 1.4526. Min Act: -0.0000

Data Index: 903656 (C4 (Web Text))

Max Activating Token Index: 678

Text #3

Max Range: 1.5914. Min Range: -1.5914

Max Act: 1.5591. Min Act: -0.0001

Data Index: 60597 (C4 (Web Text))

Max Activating Token Index: 731

Text #4

Max Range: 1.5914. Min Range: -1.5914

Max Act: 1.5385. Min Act: -0.0000

Data Index: 786123 (C4 (Web Text))

Max Activating Token Index: 214

Text #5

Max Range: 1.5914. Min Range: -1.5914

Max Act: 1.4711. Min Act: -0.0001

Data Index: 824689 (C4 (Web Text))

Max Activating Token Index: 773

Text #6

Max Range: 1.5914. Min Range: -1.5914

Max Act: 1.3393. Min Act: -0.0000

Data Index: 856608 (C4 (Web Text))

Max Activating Token Index: 237

Text #7

Max Range: 1.5914. Min Range: -1.5914

Max Act: 1.3242. Min Act: -0.0000

Data Index: 972688 (C4 (Web Text))

Max Activating Token Index: 424

Text #8

Max Range: 1.5914. Min Range: -1.5914

Max Act: 1.3363. Min Act: -0.0000

Data Index: 702701 (C4 (Web Text))

Max Activating Token Index: 669

Text #9

Max Range: 1.5914. Min Range: -1.5914

Max Act: 1.3221. Min Act: -0.0000

Data Index: 837938 (C4 (Web Text))

Max Activating Token Index: 639

Text #10

Max Range: 1.5914. Min Range: -1.5914

Max Act: 1.4499. Min Act: -0.0001

Data Index: 844913 (C4 (Web Text))

Max Activating Token Index: 235

Text #11

Max Range: 1.5914. Min Range: -1.5914

Max Act: 1.2944. Min Act: -0.0000

Data Index: 197686 (C4 (Web Text))

Max Activating Token Index: 738

Text #12

Max Range: 1.5914. Min Range: -1.5914

Max Act: 1.3215. Min Act: -0.0000

Data Index: 59196 (C4 (Web Text))

Max Activating Token Index: 1016

Text #13

Max Range: 1.5914. Min Range: -1.5914

Max Act: 1.2108. Min Act: -0.0000

Data Index: 7381 (C4 (Web Text))

Max Activating Token Index: 324

Text #14

Max Range: 1.5914. Min Range: -1.5914

Max Act: 1.2782. Min Act: -0.0000

Data Index: 828032 (C4 (Web Text))

Max Activating Token Index: 2

Text #15

Max Range: 1.5914. Min Range: -1.5914

Max Act: 1.1827. Min Act: -0.0001

Data Index: 307984 (C4 (Web Text))

Max Activating Token Index: 282

Text #16

Max Range: 1.5914. Min Range: -1.5914

Max Act: 1.2873. Min Act: -0.0001

Data Index: 1264164 (C4 (Web Text))

Max Activating Token Index: 689

Text #17

Max Range: 1.5914. Min Range: -1.5914

Max Act: 1.2916. Min Act: -0.0000

Data Index: 312257 (C4 (Web Text))

Max Activating Token Index: 13

Text #18

Max Range: 1.5914. Min Range: -1.5914

Max Act: 1.2844. Min Act: -0.0000

Data Index: 1135593 (C4 (Web Text))

Max Activating Token Index: 740

Text #19

Max Range: 1.5914. Min Range: -1.5914

Max Act: 1.2326. Min Act: -0.0000

Data Index: 974506 (C4 (Web Text))

Max Activating Token Index: 843