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

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

Neuron 1427 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: 0.9706. Min Range: -0.9706

Max Act: 0.9706. Min Act: -0.0000

Data Index: 428974 (C4 (Web Text))

Max Activating Token Index: 880

Text #1

Max Range: 0.9706. Min Range: -0.9706

Max Act: 0.6748. Min Act: -0.0000

Data Index: 696829 (C4 (Web Text))

Max Activating Token Index: 429

Text #2

Max Range: 0.9706. Min Range: -0.9706

Max Act: 0.5213. Min Act: -0.0000

Data Index: 681088 (C4 (Web Text))

Max Activating Token Index: 406

Text #3

Max Range: 0.9706. Min Range: -0.9706

Max Act: 0.5224. Min Act: -0.0000

Data Index: 887927 (C4 (Web Text))

Max Activating Token Index: 924

Text #4

Max Range: 0.9706. Min Range: -0.9706

Max Act: 0.4563. Min Act: -0.0000

Data Index: 589653 (C4 (Web Text))

Max Activating Token Index: 323

Text #5

Max Range: 0.9706. Min Range: -0.9706

Max Act: 0.4677. Min Act: -0.0000

Data Index: 853365 (C4 (Web Text))

Max Activating Token Index: 745

Text #6

Max Range: 0.9706. Min Range: -0.9706

Max Act: 0.4104. Min Act: -0.0000

Data Index: 76287 (C4 (Web Text))

Max Activating Token Index: 901

Text #7

Max Range: 0.9706. Min Range: -0.9706

Max Act: 0.4231. Min Act: -0.0000

Data Index: 404550 (C4 (Web Text))

Max Activating Token Index: 808

Text #8

Max Range: 0.9706. Min Range: -0.9706

Max Act: 0.4307. Min Act: -0.0000

Data Index: 242359 (C4 (Web Text))

Max Activating Token Index: 950

Text #9

Max Range: 0.9706. Min Range: -0.9706

Max Act: 0.4124. Min Act: -0.0000

Data Index: 1204530 (C4 (Web Text))

Max Activating Token Index: 101

Text #10

Max Range: 0.9706. Min Range: -0.9706

Max Act: 0.4121. Min Act: -0.0000

Data Index: 1305064 (C4 (Web Text))

Max Activating Token Index: 15

Text #11

Max Range: 0.9706. Min Range: -0.9706

Max Act: 0.4149. Min Act: -0.0000

Data Index: 623548 (C4 (Web Text))

Max Activating Token Index: 626

Text #12

Max Range: 0.9706. Min Range: -0.9706

Max Act: 0.3941. Min Act: -0.0000

Data Index: 780457 (C4 (Web Text))

Max Activating Token Index: 900

Text #13

Max Range: 0.9706. Min Range: -0.9706

Max Act: 0.4070. Min Act: -0.0000

Data Index: 1083637 (C4 (Web Text))

Max Activating Token Index: 109

Text #14

Max Range: 0.9706. Min Range: -0.9706

Max Act: 0.4137. Min Act: -0.0000

Data Index: 1236714 (C4 (Web Text))

Max Activating Token Index: 967

Text #15

Max Range: 0.9706. Min Range: -0.9706

Max Act: 0.4157. Min Act: -0.0000

Data Index: 239002 (C4 (Web Text))

Max Activating Token Index: 558

Text #16

Max Range: 0.9706. Min Range: -0.9706

Max Act: 0.3672. Min Act: -0.0000

Data Index: 376830 (C4 (Web Text))

Max Activating Token Index: 953

Text #17

Max Range: 0.9706. Min Range: -0.9706

Max Act: 0.4259. Min Act: -0.0000

Data Index: 5731 (C4 (Web Text))

Max Activating Token Index: 753

Text #18

Max Range: 0.9706. Min Range: -0.9706

Max Act: 0.3751. Min Act: -0.0000

Data Index: 372195 (C4 (Web Text))

Max Activating Token Index: 461

Text #19

Max Range: 0.9706. Min Range: -0.9706

Max Act: 0.3963. Min Act: -0.0000

Data Index: 1062460 (C4 (Web Text))

Max Activating Token Index: 623