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

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

Neuron 6113 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0411. Min Range: -3.0411

Max Act: 2.8981. Min Act: -0.0001

Data Index: 1052179 (C4 (Web Text))

Max Activating Token Index: 908

Text #1

Max Range: 3.0411. Min Range: -3.0411

Max Act: 2.7316. Min Act: -0.0001

Data Index: 383004 (C4 (Web Text))

Max Activating Token Index: 896

Text #2

Max Range: 3.0411. Min Range: -3.0411

Max Act: 2.8096. Min Act: -0.0001

Data Index: 912627 (C4 (Web Text))

Max Activating Token Index: 1022

Text #3

Max Range: 3.0411. Min Range: -3.0411

Max Act: 2.6878. Min Act: -0.0000

Data Index: 1070902 (C4 (Web Text))

Max Activating Token Index: 438

Text #4

Max Range: 3.0411. Min Range: -3.0411

Max Act: 3.0411. Min Act: -0.0001

Data Index: 535327 (C4 (Web Text))

Max Activating Token Index: 193

Text #5

Max Range: 3.0411. Min Range: -3.0411

Max Act: 2.6618. Min Act: -0.0001

Data Index: 432503 (C4 (Web Text))

Max Activating Token Index: 629

Text #6

Max Range: 3.0411. Min Range: -3.0411

Max Act: 2.3873. Min Act: -0.0001

Data Index: 501006 (C4 (Web Text))

Max Activating Token Index: 561

Text #7

Max Range: 3.0411. Min Range: -3.0411

Max Act: 2.6187. Min Act: -0.0001

Data Index: 192482 (C4 (Web Text))

Max Activating Token Index: 191

Text #8

Max Range: 3.0411. Min Range: -3.0411

Max Act: 2.8667. Min Act: -0.0001

Data Index: 664558 (C4 (Web Text))

Max Activating Token Index: 664

Text #9

Max Range: 3.0411. Min Range: -3.0411

Max Act: 2.5087. Min Act: -0.0000

Data Index: 1622057 (Python Code)

Max Activating Token Index: 910

Text #10

Max Range: 3.0411. Min Range: -3.0411

Max Act: 2.5249. Min Act: -0.0001

Data Index: 41953 (C4 (Web Text))

Max Activating Token Index: 871

Text #11

Max Range: 3.0411. Min Range: -3.0411

Max Act: 2.7617. Min Act: -0.0000

Data Index: 640302 (C4 (Web Text))

Max Activating Token Index: 374

Text #12

Max Range: 3.0411. Min Range: -3.0411

Max Act: 2.5973. Min Act: -0.0001

Data Index: 712527 (C4 (Web Text))

Max Activating Token Index: 445

Text #13

Max Range: 3.0411. Min Range: -3.0411

Max Act: 2.5827. Min Act: -0.0000

Data Index: 388656 (C4 (Web Text))

Max Activating Token Index: 753

Text #14

Max Range: 3.0411. Min Range: -3.0411

Max Act: 2.3982. Min Act: -0.0000

Data Index: 442716 (C4 (Web Text))

Max Activating Token Index: 33

Text #15

Max Range: 3.0411. Min Range: -3.0411

Max Act: 2.4011. Min Act: -0.0001

Data Index: 1183107 (C4 (Web Text))

Max Activating Token Index: 533

Text #16

Max Range: 3.0411. Min Range: -3.0411

Max Act: 2.5087. Min Act: -0.0001

Data Index: 551137 (C4 (Web Text))

Max Activating Token Index: 71

Text #17

Max Range: 3.0411. Min Range: -3.0411

Max Act: 2.3886. Min Act: -0.0000

Data Index: 806854 (C4 (Web Text))

Max Activating Token Index: 942

Text #18

Max Range: 3.0411. Min Range: -3.0411

Max Act: 2.3233. Min Act: -0.0001

Data Index: 1310817 (C4 (Web Text))

Max Activating Token Index: 968

Text #19

Max Range: 3.0411. Min Range: -3.0411

Max Act: 2.2260. Min Act: -0.0000

Data Index: 1320835 (C4 (Web Text))

Max Activating Token Index: 980