Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3630 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9274. Min Range: -0.9274

Max Act: 0.9274. Min Act: -0.0002

Data Index: 646656 (C4 (Web Text))

Max Activating Token Index: 668

Text #1

Max Range: 0.9274. Min Range: -0.9274

Max Act: 0.7072. Min Act: -0.0002

Data Index: 788360 (C4 (Web Text))

Max Activating Token Index: 445

Text #2

Max Range: 0.9274. Min Range: -0.9274

Max Act: 0.6756. Min Act: -0.0002

Data Index: 904587 (C4 (Web Text))

Max Activating Token Index: 645

Text #3

Max Range: 0.9274. Min Range: -0.9274

Max Act: 0.6657. Min Act: -0.0002

Data Index: 569861 (C4 (Web Text))

Max Activating Token Index: 904

Text #4

Max Range: 0.9274. Min Range: -0.9274

Max Act: 0.6110. Min Act: -0.0002

Data Index: 1355801 (C4 (Web Text))

Max Activating Token Index: 600

Text #5

Max Range: 0.9274. Min Range: -0.9274

Max Act: 0.6048. Min Act: -0.0002

Data Index: 781470 (C4 (Web Text))

Max Activating Token Index: 248

Text #6

Max Range: 0.9274. Min Range: -0.9274

Max Act: 0.5773. Min Act: -0.0002

Data Index: 744551 (C4 (Web Text))

Max Activating Token Index: 519

Text #7

Max Range: 0.9274. Min Range: -0.9274

Max Act: 0.5337. Min Act: -0.0002

Data Index: 784884 (C4 (Web Text))

Max Activating Token Index: 761

Text #8

Max Range: 0.9274. Min Range: -0.9274

Max Act: 0.5084. Min Act: -0.0002

Data Index: 707731 (C4 (Web Text))

Max Activating Token Index: 728

Text #9

Max Range: 0.9274. Min Range: -0.9274

Max Act: 0.5073. Min Act: -0.0002

Data Index: 834921 (C4 (Web Text))

Max Activating Token Index: 926

Text #10

Max Range: 0.9274. Min Range: -0.9274

Max Act: 0.5016. Min Act: -0.0002

Data Index: 124945 (C4 (Web Text))

Max Activating Token Index: 506

Text #11

Max Range: 0.9274. Min Range: -0.9274

Max Act: 0.4951. Min Act: -0.0002

Data Index: 141441 (C4 (Web Text))

Max Activating Token Index: 65

Text #12

Max Range: 0.9274. Min Range: -0.9274

Max Act: 0.4642. Min Act: -0.0002

Data Index: 400513 (C4 (Web Text))

Max Activating Token Index: 152

Text #13

Max Range: 0.9274. Min Range: -0.9274

Max Act: 0.4561. Min Act: -0.0002

Data Index: 588444 (C4 (Web Text))

Max Activating Token Index: 530

Text #14

Max Range: 0.9274. Min Range: -0.9274

Max Act: 0.4825. Min Act: -0.0002

Data Index: 912219 (C4 (Web Text))

Max Activating Token Index: 641

Text #15

Max Range: 0.9274. Min Range: -0.9274

Max Act: 0.4659. Min Act: -0.0002

Data Index: 451034 (C4 (Web Text))

Max Activating Token Index: 65

Text #16

Max Range: 0.9274. Min Range: -0.9274

Max Act: 0.4651. Min Act: -0.0002

Data Index: 734836 (C4 (Web Text))

Max Activating Token Index: 307

Text #17

Max Range: 0.9274. Min Range: -0.9274

Max Act: 0.4579. Min Act: -0.0002

Data Index: 944103 (C4 (Web Text))

Max Activating Token Index: 153

Text #18

Max Range: 0.9274. Min Range: -0.9274

Max Act: 0.4493. Min Act: -0.0003

Data Index: 1329801 (C4 (Web Text))

Max Activating Token Index: 155

Text #19

Max Range: 0.9274. Min Range: -0.9274

Max Act: 0.4491. Min Act: -0.0002

Data Index: 664259 (C4 (Web Text))

Max Activating Token Index: 753