Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 79 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.8628. Min Range: -1.8628

Max Act: 1.8628. Min Act: -0.0000

Data Index: 55821 (C4 (Web Text))

Max Activating Token Index: 476

Text #1

Max Range: 1.8628. Min Range: -1.8628

Max Act: 1.7898. Min Act: -0.0000

Data Index: 1188632 (C4 (Web Text))

Max Activating Token Index: 731

Text #2

Max Range: 1.8628. Min Range: -1.8628

Max Act: 1.6772. Min Act: -0.0000

Data Index: 611571 (C4 (Web Text))

Max Activating Token Index: 425

Text #3

Max Range: 1.8628. Min Range: -1.8628

Max Act: 1.7063. Min Act: -0.0000

Data Index: 720451 (C4 (Web Text))

Max Activating Token Index: 329

Text #4

Max Range: 1.8628. Min Range: -1.8628

Max Act: 1.6321. Min Act: -0.0000

Data Index: 137718 (C4 (Web Text))

Max Activating Token Index: 347

Text #5

Max Range: 1.8628. Min Range: -1.8628

Max Act: 1.7363. Min Act: -0.0000

Data Index: 452441 (C4 (Web Text))

Max Activating Token Index: 1007

Text #6

Max Range: 1.8628. Min Range: -1.8628

Max Act: 1.6415. Min Act: -0.0000

Data Index: 228678 (C4 (Web Text))

Max Activating Token Index: 933

Text #7

Max Range: 1.8628. Min Range: -1.8628

Max Act: 1.5979. Min Act: -0.0000

Data Index: 1316044 (C4 (Web Text))

Max Activating Token Index: 477

Text #8

Max Range: 1.8628. Min Range: -1.8628

Max Act: 1.4937. Min Act: -0.0000

Data Index: 648664 (C4 (Web Text))

Max Activating Token Index: 85

Text #9

Max Range: 1.8628. Min Range: -1.8628

Max Act: 1.4844. Min Act: -0.0000

Data Index: 457857 (C4 (Web Text))

Max Activating Token Index: 232

Text #10

Max Range: 1.8628. Min Range: -1.8628

Max Act: 1.5411. Min Act: -0.0000

Data Index: 1318307 (C4 (Web Text))

Max Activating Token Index: 338

Text #11

Max Range: 1.8628. Min Range: -1.8628

Max Act: 1.4199. Min Act: -0.0000

Data Index: 834483 (C4 (Web Text))

Max Activating Token Index: 772

Text #12

Max Range: 1.8628. Min Range: -1.8628

Max Act: 1.3961. Min Act: -0.0000

Data Index: 457154 (C4 (Web Text))

Max Activating Token Index: 968

Text #13

Max Range: 1.8628. Min Range: -1.8628

Max Act: 1.3257. Min Act: -0.0000

Data Index: 1347816 (C4 (Web Text))

Max Activating Token Index: 974

Text #14

Max Range: 1.8628. Min Range: -1.8628

Max Act: 1.3529. Min Act: -0.0000

Data Index: 543554 (C4 (Web Text))

Max Activating Token Index: 630

Text #15

Max Range: 1.8628. Min Range: -1.8628

Max Act: 1.3079. Min Act: -0.0000

Data Index: 1236091 (C4 (Web Text))

Max Activating Token Index: 609

Text #16

Max Range: 1.8628. Min Range: -1.8628

Max Act: 1.2918. Min Act: -0.0000

Data Index: 820908 (C4 (Web Text))

Max Activating Token Index: 693

Text #17

Max Range: 1.8628. Min Range: -1.8628

Max Act: 1.2992. Min Act: -0.0000

Data Index: 523227 (C4 (Web Text))

Max Activating Token Index: 356

Text #18

Max Range: 1.8628. Min Range: -1.8628

Max Act: 1.2937. Min Act: -0.0000

Data Index: 41753 (C4 (Web Text))

Max Activating Token Index: 1003

Text #19

Max Range: 1.8628. Min Range: -1.8628

Max Act: 1.2738. Min Act: -0.0000

Data Index: 1445802 (Python Code)

Max Activating Token Index: 356