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

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

Neuron 3448 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6621. Min Range: -0.6621

Max Act: 0.6621. Min Act: -0.0000

Data Index: 1291362 (C4 (Web Text))

Max Activating Token Index: 138

Text #1

Max Range: 0.6621. Min Range: -0.6621

Max Act: 0.5784. Min Act: -0.0000

Data Index: 997120 (C4 (Web Text))

Max Activating Token Index: 543

Text #2

Max Range: 0.6621. Min Range: -0.6621

Max Act: 0.5583. Min Act: -0.0000

Data Index: 906574 (C4 (Web Text))

Max Activating Token Index: 259

Text #3

Max Range: 0.6621. Min Range: -0.6621

Max Act: 0.5277. Min Act: -0.0000

Data Index: 845204 (C4 (Web Text))

Max Activating Token Index: 737

Text #4

Max Range: 0.6621. Min Range: -0.6621

Max Act: 0.5418. Min Act: -0.0000

Data Index: 1070296 (C4 (Web Text))

Max Activating Token Index: 625

Text #5

Max Range: 0.6621. Min Range: -0.6621

Max Act: 0.5165. Min Act: -0.0000

Data Index: 1224693 (C4 (Web Text))

Max Activating Token Index: 739

Text #6

Max Range: 0.6621. Min Range: -0.6621

Max Act: 0.4708. Min Act: -0.0000

Data Index: 1012463 (C4 (Web Text))

Max Activating Token Index: 584

Text #7

Max Range: 0.6621. Min Range: -0.6621

Max Act: 0.4841. Min Act: -0.0000

Data Index: 903467 (C4 (Web Text))

Max Activating Token Index: 846

Text #8

Max Range: 0.6621. Min Range: -0.6621

Max Act: 0.4417. Min Act: -0.0000

Data Index: 208026 (C4 (Web Text))

Max Activating Token Index: 321

Text #9

Max Range: 0.6621. Min Range: -0.6621

Max Act: 0.4705. Min Act: -0.0000

Data Index: 1172017 (C4 (Web Text))

Max Activating Token Index: 583

Text #10

Max Range: 0.6621. Min Range: -0.6621

Max Act: 0.4156. Min Act: -0.0000

Data Index: 980792 (C4 (Web Text))

Max Activating Token Index: 1014

Text #11

Max Range: 0.6621. Min Range: -0.6621

Max Act: 0.4404. Min Act: -0.0000

Data Index: 954263 (C4 (Web Text))

Max Activating Token Index: 940

Text #12

Max Range: 0.6621. Min Range: -0.6621

Max Act: 0.4383. Min Act: -0.0000

Data Index: 819481 (C4 (Web Text))

Max Activating Token Index: 508

Text #13

Max Range: 0.6621. Min Range: -0.6621

Max Act: 0.4601. Min Act: -0.0000

Data Index: 1007834 (C4 (Web Text))

Max Activating Token Index: 73

Text #14

Max Range: 0.6621. Min Range: -0.6621

Max Act: 0.3897. Min Act: -0.0000

Data Index: 400248 (C4 (Web Text))

Max Activating Token Index: 561

Text #15

Max Range: 0.6621. Min Range: -0.6621

Max Act: 0.3710. Min Act: -0.0000

Data Index: 682812 (C4 (Web Text))

Max Activating Token Index: 551

Text #16

Max Range: 0.6621. Min Range: -0.6621

Max Act: 0.3696. Min Act: -0.0000

Data Index: 1472787 (Python Code)

Max Activating Token Index: 355

Text #17

Max Range: 0.6621. Min Range: -0.6621

Max Act: 0.4064. Min Act: -0.0000

Data Index: 1156899 (C4 (Web Text))

Max Activating Token Index: 371

Text #18

Max Range: 0.6621. Min Range: -0.6621

Max Act: 0.4298. Min Act: -0.0000

Data Index: 206620 (C4 (Web Text))

Max Activating Token Index: 746

Text #19

Max Range: 0.6621. Min Range: -0.6621

Max Act: 0.3838. Min Act: -0.0000

Data Index: 1117976 (C4 (Web Text))

Max Activating Token Index: 585