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

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

Neuron 5555 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7000. Min Range: -0.7000

Max Act: 0.7000. Min Act: -0.0000

Data Index: 533407 (C4 (Web Text))

Max Activating Token Index: 157

Text #1

Max Range: 0.7000. Min Range: -0.7000

Max Act: 0.6425. Min Act: -0.0000

Data Index: 1285283 (C4 (Web Text))

Max Activating Token Index: 698

Text #2

Max Range: 0.7000. Min Range: -0.7000

Max Act: 0.6414. Min Act: -0.0000

Data Index: 1211616 (C4 (Web Text))

Max Activating Token Index: 848

Text #3

Max Range: 0.7000. Min Range: -0.7000

Max Act: 0.5851. Min Act: -0.0000

Data Index: 746992 (C4 (Web Text))

Max Activating Token Index: 411

Text #4

Max Range: 0.7000. Min Range: -0.7000

Max Act: 0.5942. Min Act: 0.0000

Data Index: 496917 (C4 (Web Text))

Max Activating Token Index: 313

Text #5

Max Range: 0.7000. Min Range: -0.7000

Max Act: 0.5897. Min Act: -0.0000

Data Index: 341837 (C4 (Web Text))

Max Activating Token Index: 933

Text #6

Max Range: 0.7000. Min Range: -0.7000

Max Act: 0.5581. Min Act: -0.0000

Data Index: 1213624 (C4 (Web Text))

Max Activating Token Index: 456

Text #7

Max Range: 0.7000. Min Range: -0.7000

Max Act: 0.5347. Min Act: -0.0000

Data Index: 222245 (C4 (Web Text))

Max Activating Token Index: 707

Text #8

Max Range: 0.7000. Min Range: -0.7000

Max Act: 0.5622. Min Act: -0.0000

Data Index: 793651 (C4 (Web Text))

Max Activating Token Index: 707

Text #9

Max Range: 0.7000. Min Range: -0.7000

Max Act: 0.5306. Min Act: -0.0000

Data Index: 1065027 (C4 (Web Text))

Max Activating Token Index: 1010

Text #10

Max Range: 0.7000. Min Range: -0.7000

Max Act: 0.5277. Min Act: -0.0000

Data Index: 1218352 (C4 (Web Text))

Max Activating Token Index: 900

Text #11

Max Range: 0.7000. Min Range: -0.7000

Max Act: 0.4984. Min Act: -0.0000

Data Index: 532256 (C4 (Web Text))

Max Activating Token Index: 986

Text #12

Max Range: 0.7000. Min Range: -0.7000

Max Act: 0.5151. Min Act: -0.0000

Data Index: 1090746 (C4 (Web Text))

Max Activating Token Index: 439

Text #13

Max Range: 0.7000. Min Range: -0.7000

Max Act: 0.5150. Min Act: -0.0000

Data Index: 140286 (C4 (Web Text))

Max Activating Token Index: 266

Text #14

Max Range: 0.7000. Min Range: -0.7000

Max Act: 0.5132. Min Act: -0.0000

Data Index: 1225666 (C4 (Web Text))

Max Activating Token Index: 253

Text #15

Max Range: 0.7000. Min Range: -0.7000

Max Act: 0.5281. Min Act: -0.0000

Data Index: 759689 (C4 (Web Text))

Max Activating Token Index: 895

Text #16

Max Range: 0.7000. Min Range: -0.7000

Max Act: 0.5121. Min Act: -0.0000

Data Index: 849806 (C4 (Web Text))

Max Activating Token Index: 32

Text #17

Max Range: 0.7000. Min Range: -0.7000

Max Act: 0.5077. Min Act: -0.0000

Data Index: 1268721 (C4 (Web Text))

Max Activating Token Index: 480

Text #18

Max Range: 0.7000. Min Range: -0.7000

Max Act: 0.4917. Min Act: -0.0000

Data Index: 66369 (C4 (Web Text))

Max Activating Token Index: 409

Text #19

Max Range: 0.7000. Min Range: -0.7000

Max Act: 0.5210. Min Act: -0.0000

Data Index: 770918 (C4 (Web Text))

Max Activating Token Index: 785