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

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

Neuron 132 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: 0.8986. Min Range: -0.8986

Max Act: 0.8986. Min Act: -0.0000

Data Index: 371771 (C4 (Web Text))

Max Activating Token Index: 519

Text #1

Max Range: 0.8986. Min Range: -0.8986

Max Act: 0.7897. Min Act: -0.0000

Data Index: 1011453 (C4 (Web Text))

Max Activating Token Index: 1002

Text #2

Max Range: 0.8986. Min Range: -0.8986

Max Act: 0.8421. Min Act: -0.0000

Data Index: 850587 (C4 (Web Text))

Max Activating Token Index: 18

Text #3

Max Range: 0.8986. Min Range: -0.8986

Max Act: 0.7705. Min Act: -0.0000

Data Index: 969240 (C4 (Web Text))

Max Activating Token Index: 714

Text #4

Max Range: 0.8986. Min Range: -0.8986

Max Act: 0.7870. Min Act: -0.0000

Data Index: 176479 (C4 (Web Text))

Max Activating Token Index: 799

Text #5

Max Range: 0.8986. Min Range: -0.8986

Max Act: 0.7581. Min Act: -0.0000

Data Index: 432542 (C4 (Web Text))

Max Activating Token Index: 254

Text #6

Max Range: 0.8986. Min Range: -0.8986

Max Act: 0.7244. Min Act: -0.0000

Data Index: 126470 (C4 (Web Text))

Max Activating Token Index: 183

Text #7

Max Range: 0.8986. Min Range: -0.8986

Max Act: 0.7388. Min Act: -0.0000

Data Index: 1133136 (C4 (Web Text))

Max Activating Token Index: 275

Text #8

Max Range: 0.8986. Min Range: -0.8986

Max Act: 0.6996. Min Act: -0.0000

Data Index: 227610 (C4 (Web Text))

Max Activating Token Index: 711

Text #9

Max Range: 0.8986. Min Range: -0.8986

Max Act: 0.6851. Min Act: -0.0000

Data Index: 1033799 (C4 (Web Text))

Max Activating Token Index: 370

Text #10

Max Range: 0.8986. Min Range: -0.8986

Max Act: 0.7109. Min Act: -0.0000

Data Index: 390365 (C4 (Web Text))

Max Activating Token Index: 31

Text #11

Max Range: 0.8986. Min Range: -0.8986

Max Act: 0.7027. Min Act: -0.0000

Data Index: 995345 (C4 (Web Text))

Max Activating Token Index: 331

Text #12

Max Range: 0.8986. Min Range: -0.8986

Max Act: 0.6977. Min Act: -0.0000

Data Index: 329780 (C4 (Web Text))

Max Activating Token Index: 439

Text #13

Max Range: 0.8986. Min Range: -0.8986

Max Act: 0.6986. Min Act: -0.0000

Data Index: 1256785 (C4 (Web Text))

Max Activating Token Index: 621

Text #14

Max Range: 0.8986. Min Range: -0.8986

Max Act: 0.7394. Min Act: -0.0000

Data Index: 1235160 (C4 (Web Text))

Max Activating Token Index: 916

Text #15

Max Range: 0.8986. Min Range: -0.8986

Max Act: 0.6477. Min Act: -0.0000

Data Index: 266341 (C4 (Web Text))

Max Activating Token Index: 386

Text #16

Max Range: 0.8986. Min Range: -0.8986

Max Act: 0.6890. Min Act: -0.0000

Data Index: 737173 (C4 (Web Text))

Max Activating Token Index: 135

Text #17

Max Range: 0.8986. Min Range: -0.8986

Max Act: 0.6917. Min Act: -0.0000

Data Index: 1222751 (C4 (Web Text))

Max Activating Token Index: 702

Text #18

Max Range: 0.8986. Min Range: -0.8986

Max Act: 0.7091. Min Act: -0.0000

Data Index: 441954 (C4 (Web Text))

Max Activating Token Index: 800

Text #19

Max Range: 0.8986. Min Range: -0.8986

Max Act: 0.6869. Min Act: -0.0000

Data Index: 235084 (C4 (Web Text))

Max Activating Token Index: 345