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

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

Neuron 5554 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: 0.9976. Min Range: -0.9976

Max Act: 0.9962. Min Act: -0.0000

Data Index: 1304299 (C4 (Web Text))

Max Activating Token Index: 139

Text #1

Max Range: 0.9976. Min Range: -0.9976

Max Act: 0.9976. Min Act: -0.0000

Data Index: 115026 (C4 (Web Text))

Max Activating Token Index: 636

Text #2

Max Range: 0.9976. Min Range: -0.9976

Max Act: 0.7729. Min Act: -0.0000

Data Index: 1080332 (C4 (Web Text))

Max Activating Token Index: 554

Text #3

Max Range: 0.9976. Min Range: -0.9976

Max Act: 0.7502. Min Act: -0.0000

Data Index: 1244518 (C4 (Web Text))

Max Activating Token Index: 175

Text #4

Max Range: 0.9976. Min Range: -0.9976

Max Act: 0.7743. Min Act: -0.0000

Data Index: 1152448 (C4 (Web Text))

Max Activating Token Index: 666

Text #5

Max Range: 0.9976. Min Range: -0.9976

Max Act: 0.7524. Min Act: -0.0000

Data Index: 773081 (C4 (Web Text))

Max Activating Token Index: 341

Text #6

Max Range: 0.9976. Min Range: -0.9976

Max Act: 0.6981. Min Act: -0.0000

Data Index: 1328772 (C4 (Web Text))

Max Activating Token Index: 161

Text #7

Max Range: 0.9976. Min Range: -0.9976

Max Act: 0.7201. Min Act: -0.0000

Data Index: 714994 (C4 (Web Text))

Max Activating Token Index: 245

Text #8

Max Range: 0.9976. Min Range: -0.9976

Max Act: 0.7130. Min Act: -0.0000

Data Index: 1033789 (C4 (Web Text))

Max Activating Token Index: 656

Text #9

Max Range: 0.9976. Min Range: -0.9976

Max Act: 0.7316. Min Act: -0.0000

Data Index: 858902 (C4 (Web Text))

Max Activating Token Index: 609

Text #10

Max Range: 0.9976. Min Range: -0.9976

Max Act: 0.6844. Min Act: -0.0000

Data Index: 29070 (C4 (Web Text))

Max Activating Token Index: 900

Text #11

Max Range: 0.9976. Min Range: -0.9976

Max Act: 0.7414. Min Act: -0.0000

Data Index: 175859 (C4 (Web Text))

Max Activating Token Index: 343

Text #12

Max Range: 0.9976. Min Range: -0.9976

Max Act: 0.6955. Min Act: -0.0000

Data Index: 450606 (C4 (Web Text))

Max Activating Token Index: 382

Text #13

Max Range: 0.9976. Min Range: -0.9976

Max Act: 0.7382. Min Act: -0.0000

Data Index: 1147311 (C4 (Web Text))

Max Activating Token Index: 384

Text #14

Max Range: 0.9976. Min Range: -0.9976

Max Act: 0.7113. Min Act: -0.0000

Data Index: 323244 (C4 (Web Text))

Max Activating Token Index: 415

Text #15

Max Range: 0.9976. Min Range: -0.9976

Max Act: 0.6722. Min Act: -0.0000

Data Index: 756781 (C4 (Web Text))

Max Activating Token Index: 163

Text #16

Max Range: 0.9976. Min Range: -0.9976

Max Act: 0.6601. Min Act: -0.0000

Data Index: 23312 (C4 (Web Text))

Max Activating Token Index: 486

Text #17

Max Range: 0.9976. Min Range: -0.9976

Max Act: 0.7016. Min Act: -0.0000

Data Index: 770202 (C4 (Web Text))

Max Activating Token Index: 447

Text #18

Max Range: 0.9976. Min Range: -0.9976

Max Act: 0.7002. Min Act: -0.0000

Data Index: 894351 (C4 (Web Text))

Max Activating Token Index: 592

Text #19

Max Range: 0.9976. Min Range: -0.9976

Max Act: 0.7103. Min Act: -0.0000

Data Index: 343425 (C4 (Web Text))

Max Activating Token Index: 52