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

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

Neuron 530 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3465. Min Range: -1.3465

Max Act: 1.3465. Min Act: -0.0000

Data Index: 1060058 (C4 (Web Text))

Max Activating Token Index: 269

Text #1

Max Range: 1.3465. Min Range: -1.3465

Max Act: 1.0884. Min Act: -0.0000

Data Index: 664463 (C4 (Web Text))

Max Activating Token Index: 497

Text #2

Max Range: 1.3465. Min Range: -1.3465

Max Act: 1.0760. Min Act: -0.0000

Data Index: 1087707 (C4 (Web Text))

Max Activating Token Index: 414

Text #3

Max Range: 1.3465. Min Range: -1.3465

Max Act: 1.0071. Min Act: -0.0000

Data Index: 758295 (C4 (Web Text))

Max Activating Token Index: 538

Text #4

Max Range: 1.3465. Min Range: -1.3465

Max Act: 1.0748. Min Act: -0.0000

Data Index: 568278 (C4 (Web Text))

Max Activating Token Index: 606

Text #5

Max Range: 1.3465. Min Range: -1.3465

Max Act: 0.8677. Min Act: -0.0000

Data Index: 717824 (C4 (Web Text))

Max Activating Token Index: 857

Text #6

Max Range: 1.3465. Min Range: -1.3465

Max Act: 0.8651. Min Act: -0.0000

Data Index: 958393 (C4 (Web Text))

Max Activating Token Index: 879

Text #7

Max Range: 1.3465. Min Range: -1.3465

Max Act: 0.8497. Min Act: -0.0000

Data Index: 435293 (C4 (Web Text))

Max Activating Token Index: 120

Text #8

Max Range: 1.3465. Min Range: -1.3465

Max Act: 0.8037. Min Act: -0.0000

Data Index: 50477 (C4 (Web Text))

Max Activating Token Index: 717

Text #9

Max Range: 1.3465. Min Range: -1.3465

Max Act: 0.8244. Min Act: -0.0000

Data Index: 280305 (C4 (Web Text))

Max Activating Token Index: 4

Text #10

Max Range: 1.3465. Min Range: -1.3465

Max Act: 0.9217. Min Act: -0.0000

Data Index: 1316621 (C4 (Web Text))

Max Activating Token Index: 728

Text #11

Max Range: 1.3465. Min Range: -1.3465

Max Act: 0.7592. Min Act: -0.0000

Data Index: 634226 (C4 (Web Text))

Max Activating Token Index: 322

Text #12

Max Range: 1.3465. Min Range: -1.3465

Max Act: 0.8069. Min Act: -0.0000

Data Index: 846163 (C4 (Web Text))

Max Activating Token Index: 630

Text #13

Max Range: 1.3465. Min Range: -1.3465

Max Act: 0.8063. Min Act: -0.0000

Data Index: 857613 (C4 (Web Text))

Max Activating Token Index: 17

Text #14

Max Range: 1.3465. Min Range: -1.3465

Max Act: 0.7331. Min Act: -0.0000

Data Index: 2335 (C4 (Web Text))

Max Activating Token Index: 258

Text #15

Max Range: 1.3465. Min Range: -1.3465

Max Act: 0.7535. Min Act: -0.0000

Data Index: 275424 (C4 (Web Text))

Max Activating Token Index: 551

Text #16

Max Range: 1.3465. Min Range: -1.3465

Max Act: 0.7548. Min Act: -0.0000

Data Index: 601022 (C4 (Web Text))

Max Activating Token Index: 152

Text #17

Max Range: 1.3465. Min Range: -1.3465

Max Act: 0.7596. Min Act: -0.0000

Data Index: 142373 (C4 (Web Text))

Max Activating Token Index: 365

Text #18

Max Range: 1.3465. Min Range: -1.3465

Max Act: 0.8253. Min Act: -0.0000

Data Index: 99825 (C4 (Web Text))

Max Activating Token Index: 989

Text #19

Max Range: 1.3465. Min Range: -1.3465

Max Act: 0.6913. Min Act: -0.0000

Data Index: 173379 (C4 (Web Text))

Max Activating Token Index: 95