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

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

Neuron 5350 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: 1.5732. Min Range: -1.5732

Max Act: 1.5483. Min Act: -0.0000

Data Index: 211409 (C4 (Web Text))

Max Activating Token Index: 209

Text #1

Max Range: 1.5732. Min Range: -1.5732

Max Act: 1.5732. Min Act: -0.0000

Data Index: 246994 (C4 (Web Text))

Max Activating Token Index: 263

Text #2

Max Range: 1.5732. Min Range: -1.5732

Max Act: 1.4831. Min Act: -0.0000

Data Index: 16470 (C4 (Web Text))

Max Activating Token Index: 734

Text #3

Max Range: 1.5732. Min Range: -1.5732

Max Act: 1.4385. Min Act: -0.0000

Data Index: 200675 (C4 (Web Text))

Max Activating Token Index: 657

Text #4

Max Range: 1.5732. Min Range: -1.5732

Max Act: 1.3982. Min Act: -0.0000

Data Index: 155540 (C4 (Web Text))

Max Activating Token Index: 429

Text #5

Max Range: 1.5732. Min Range: -1.5732

Max Act: 1.3655. Min Act: -0.0000

Data Index: 432536 (C4 (Web Text))

Max Activating Token Index: 793

Text #6

Max Range: 1.5732. Min Range: -1.5732

Max Act: 1.3418. Min Act: -0.0000

Data Index: 324713 (C4 (Web Text))

Max Activating Token Index: 934

Text #7

Max Range: 1.5732. Min Range: -1.5732

Max Act: 1.2727. Min Act: -0.0000

Data Index: 767071 (C4 (Web Text))

Max Activating Token Index: 275

Text #8

Max Range: 1.5732. Min Range: -1.5732

Max Act: 1.2633. Min Act: -0.0000

Data Index: 744924 (C4 (Web Text))

Max Activating Token Index: 775

Text #9

Max Range: 1.5732. Min Range: -1.5732

Max Act: 1.2938. Min Act: -0.0000

Data Index: 304371 (C4 (Web Text))

Max Activating Token Index: 194

Text #10

Max Range: 1.5732. Min Range: -1.5732

Max Act: 1.3128. Min Act: -0.0000

Data Index: 317715 (C4 (Web Text))

Max Activating Token Index: 970

Text #11

Max Range: 1.5732. Min Range: -1.5732

Max Act: 1.2788. Min Act: -0.0000

Data Index: 211289 (C4 (Web Text))

Max Activating Token Index: 78

Text #12

Max Range: 1.5732. Min Range: -1.5732

Max Act: 1.2843. Min Act: -0.0000

Data Index: 285271 (C4 (Web Text))

Max Activating Token Index: 633

Text #13

Max Range: 1.5732. Min Range: -1.5732

Max Act: 1.2287. Min Act: -0.0000

Data Index: 811989 (C4 (Web Text))

Max Activating Token Index: 644

Text #14

Max Range: 1.5732. Min Range: -1.5732

Max Act: 1.1905. Min Act: -0.0000

Data Index: 266797 (C4 (Web Text))

Max Activating Token Index: 47

Text #15

Max Range: 1.5732. Min Range: -1.5732

Max Act: 1.2378. Min Act: -0.0000

Data Index: 380903 (C4 (Web Text))

Max Activating Token Index: 485

Text #16

Max Range: 1.5732. Min Range: -1.5732

Max Act: 1.2348. Min Act: -0.0000

Data Index: 98784 (C4 (Web Text))

Max Activating Token Index: 103

Text #17

Max Range: 1.5732. Min Range: -1.5732

Max Act: 1.1963. Min Act: -0.0000

Data Index: 1079999 (C4 (Web Text))

Max Activating Token Index: 683

Text #18

Max Range: 1.5732. Min Range: -1.5732

Max Act: 1.1818. Min Act: -0.0000

Data Index: 1118898 (C4 (Web Text))

Max Activating Token Index: 566

Text #19

Max Range: 1.5732. Min Range: -1.5732

Max Act: 1.2293. Min Act: -0.0000

Data Index: 978762 (C4 (Web Text))

Max Activating Token Index: 540