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

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

Neuron 2044 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8163. Min Range: -0.8163

Max Act: 0.8163. Min Act: -0.0000

Data Index: 54523 (C4 (Web Text))

Max Activating Token Index: 474

Text #1

Max Range: 0.8163. Min Range: -0.8163

Max Act: 0.6878. Min Act: -0.0000

Data Index: 640740 (C4 (Web Text))

Max Activating Token Index: 288

Text #2

Max Range: 0.8163. Min Range: -0.8163

Max Act: 0.6468. Min Act: -0.0000

Data Index: 508717 (C4 (Web Text))

Max Activating Token Index: 656

Text #3

Max Range: 0.8163. Min Range: -0.8163

Max Act: 0.6210. Min Act: 0.0001

Data Index: 1340021 (C4 (Web Text))

Max Activating Token Index: 475

Text #4

Max Range: 0.8163. Min Range: -0.8163

Max Act: 0.6410. Min Act: -0.0000

Data Index: 727810 (C4 (Web Text))

Max Activating Token Index: 471

Text #5

Max Range: 0.8163. Min Range: -0.8163

Max Act: 0.6394. Min Act: -0.0000

Data Index: 873490 (C4 (Web Text))

Max Activating Token Index: 971

Text #6

Max Range: 0.8163. Min Range: -0.8163

Max Act: 0.6410. Min Act: -0.0000

Data Index: 408002 (C4 (Web Text))

Max Activating Token Index: 500

Text #7

Max Range: 0.8163. Min Range: -0.8163

Max Act: 0.6149. Min Act: -0.0000

Data Index: 588503 (C4 (Web Text))

Max Activating Token Index: 535

Text #8

Max Range: 0.8163. Min Range: -0.8163

Max Act: 0.5845. Min Act: -0.0000

Data Index: 33672 (C4 (Web Text))

Max Activating Token Index: 506

Text #9

Max Range: 0.8163. Min Range: -0.8163

Max Act: 0.5640. Min Act: -0.0000

Data Index: 410798 (C4 (Web Text))

Max Activating Token Index: 726

Text #10

Max Range: 0.8163. Min Range: -0.8163

Max Act: 0.5642. Min Act: -0.0000

Data Index: 1075763 (C4 (Web Text))

Max Activating Token Index: 497

Text #11

Max Range: 0.8163. Min Range: -0.8163

Max Act: 0.5413. Min Act: -0.0000

Data Index: 181609 (C4 (Web Text))

Max Activating Token Index: 287

Text #12

Max Range: 0.8163. Min Range: -0.8163

Max Act: 0.5836. Min Act: -0.0000

Data Index: 1321995 (C4 (Web Text))

Max Activating Token Index: 618

Text #13

Max Range: 0.8163. Min Range: -0.8163

Max Act: 0.5294. Min Act: -0.0000

Data Index: 528009 (C4 (Web Text))

Max Activating Token Index: 612

Text #14

Max Range: 0.8163. Min Range: -0.8163

Max Act: 0.5593. Min Act: 0.0000

Data Index: 108755 (C4 (Web Text))

Max Activating Token Index: 260

Text #15

Max Range: 0.8163. Min Range: -0.8163

Max Act: 0.5305. Min Act: -0.0000

Data Index: 26662 (C4 (Web Text))

Max Activating Token Index: 523

Text #16

Max Range: 0.8163. Min Range: -0.8163

Max Act: 0.5077. Min Act: -0.0000

Data Index: 1174762 (C4 (Web Text))

Max Activating Token Index: 302

Text #17

Max Range: 0.8163. Min Range: -0.8163

Max Act: 0.5181. Min Act: 0.0000

Data Index: 1311565 (C4 (Web Text))

Max Activating Token Index: 420

Text #18

Max Range: 0.8163. Min Range: -0.8163

Max Act: 0.4821. Min Act: -0.0000

Data Index: 259770 (C4 (Web Text))

Max Activating Token Index: 247

Text #19

Max Range: 0.8163. Min Range: -0.8163

Max Act: 0.5102. Min Act: 0.0001

Data Index: 805948 (C4 (Web Text))

Max Activating Token Index: 655