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

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

Neuron 455 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: 1.6928. Min Range: -1.6928

Max Act: 1.6928. Min Act: -0.0000

Data Index: 197484 (C4 (Web Text))

Max Activating Token Index: 151

Text #1

Max Range: 1.6928. Min Range: -1.6928

Max Act: 1.4360. Min Act: -0.0000

Data Index: 19656 (C4 (Web Text))

Max Activating Token Index: 596

Text #2

Max Range: 1.6928. Min Range: -1.6928

Max Act: 1.3138. Min Act: -0.0000

Data Index: 746851 (C4 (Web Text))

Max Activating Token Index: 981

Text #3

Max Range: 1.6928. Min Range: -1.6928

Max Act: 1.1735. Min Act: -0.0000

Data Index: 729199 (C4 (Web Text))

Max Activating Token Index: 872

Text #4

Max Range: 1.6928. Min Range: -1.6928

Max Act: 1.1294. Min Act: -0.0000

Data Index: 849011 (C4 (Web Text))

Max Activating Token Index: 225

Text #5

Max Range: 1.6928. Min Range: -1.6928

Max Act: 0.9706. Min Act: -0.0000

Data Index: 404018 (C4 (Web Text))

Max Activating Token Index: 251

Text #6

Max Range: 1.6928. Min Range: -1.6928

Max Act: 0.9696. Min Act: -0.0000

Data Index: 835145 (C4 (Web Text))

Max Activating Token Index: 563

Text #7

Max Range: 1.6928. Min Range: -1.6928

Max Act: 0.8283. Min Act: -0.0000

Data Index: 575745 (C4 (Web Text))

Max Activating Token Index: 275

Text #8

Max Range: 1.6928. Min Range: -1.6928

Max Act: 0.9276. Min Act: -0.0000

Data Index: 1258230 (C4 (Web Text))

Max Activating Token Index: 756

Text #9

Max Range: 1.6928. Min Range: -1.6928

Max Act: 0.8162. Min Act: -0.0000

Data Index: 853816 (C4 (Web Text))

Max Activating Token Index: 271

Text #10

Max Range: 1.6928. Min Range: -1.6928

Max Act: 0.7886. Min Act: -0.0000

Data Index: 496850 (C4 (Web Text))

Max Activating Token Index: 137

Text #11

Max Range: 1.6928. Min Range: -1.6928

Max Act: 0.8295. Min Act: -0.0000

Data Index: 553655 (C4 (Web Text))

Max Activating Token Index: 293

Text #12

Max Range: 1.6928. Min Range: -1.6928

Max Act: 0.7587. Min Act: -0.0000

Data Index: 501523 (C4 (Web Text))

Max Activating Token Index: 310

Text #13

Max Range: 1.6928. Min Range: -1.6928

Max Act: 0.7466. Min Act: -0.0000

Data Index: 1264599 (C4 (Web Text))

Max Activating Token Index: 520

Text #14

Max Range: 1.6928. Min Range: -1.6928

Max Act: 0.7270. Min Act: -0.0000

Data Index: 697480 (C4 (Web Text))

Max Activating Token Index: 671

Text #15

Max Range: 1.6928. Min Range: -1.6928

Max Act: 0.7610. Min Act: -0.0000

Data Index: 166771 (C4 (Web Text))

Max Activating Token Index: 371

Text #16

Max Range: 1.6928. Min Range: -1.6928

Max Act: 0.7400. Min Act: -0.0000

Data Index: 734002 (C4 (Web Text))

Max Activating Token Index: 704

Text #17

Max Range: 1.6928. Min Range: -1.6928

Max Act: 0.7609. Min Act: -0.0000

Data Index: 690018 (C4 (Web Text))

Max Activating Token Index: 611

Text #18

Max Range: 1.6928. Min Range: -1.6928

Max Act: 0.8078. Min Act: -0.0000

Data Index: 781774 (C4 (Web Text))

Max Activating Token Index: 222

Text #19

Max Range: 1.6928. Min Range: -1.6928

Max Act: 0.7340. Min Act: -0.0000

Data Index: 880500 (C4 (Web Text))

Max Activating Token Index: 102