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

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

Neuron 2619 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7712. Min Range: -0.7712

Max Act: 0.7712. Min Act: -0.0001

Data Index: 406797 (C4 (Web Text))

Max Activating Token Index: 173

Text #1

Max Range: 0.7712. Min Range: -0.7712

Max Act: 0.7488. Min Act: -0.0000

Data Index: 946996 (C4 (Web Text))

Max Activating Token Index: 608

Text #2

Max Range: 0.7712. Min Range: -0.7712

Max Act: 0.7593. Min Act: -0.0001

Data Index: 629410 (C4 (Web Text))

Max Activating Token Index: 929

Text #3

Max Range: 0.7712. Min Range: -0.7712

Max Act: 0.6919. Min Act: -0.0001

Data Index: 1215569 (C4 (Web Text))

Max Activating Token Index: 504

Text #4

Max Range: 0.7712. Min Range: -0.7712

Max Act: 0.6652. Min Act: -0.0001

Data Index: 611223 (C4 (Web Text))

Max Activating Token Index: 579

Text #5

Max Range: 0.7712. Min Range: -0.7712

Max Act: 0.6454. Min Act: -0.0001

Data Index: 1156186 (C4 (Web Text))

Max Activating Token Index: 142

Text #6

Max Range: 0.7712. Min Range: -0.7712

Max Act: 0.6206. Min Act: -0.0000

Data Index: 1053483 (C4 (Web Text))

Max Activating Token Index: 606

Text #7

Max Range: 0.7712. Min Range: -0.7712

Max Act: 0.6534. Min Act: -0.0001

Data Index: 160219 (C4 (Web Text))

Max Activating Token Index: 140

Text #8

Max Range: 0.7712. Min Range: -0.7712

Max Act: 0.6651. Min Act: -0.0001

Data Index: 401304 (C4 (Web Text))

Max Activating Token Index: 915

Text #9

Max Range: 0.7712. Min Range: -0.7712

Max Act: 0.5689. Min Act: -0.0001

Data Index: 191506 (C4 (Web Text))

Max Activating Token Index: 740

Text #10

Max Range: 0.7712. Min Range: -0.7712

Max Act: 0.6278. Min Act: -0.0000

Data Index: 859533 (C4 (Web Text))

Max Activating Token Index: 636

Text #11

Max Range: 0.7712. Min Range: -0.7712

Max Act: 0.6211. Min Act: -0.0001

Data Index: 232103 (C4 (Web Text))

Max Activating Token Index: 720

Text #12

Max Range: 0.7712. Min Range: -0.7712

Max Act: 0.6183. Min Act: -0.0000

Data Index: 388549 (C4 (Web Text))

Max Activating Token Index: 806

Text #13

Max Range: 0.7712. Min Range: -0.7712

Max Act: 0.5781. Min Act: -0.0000

Data Index: 495698 (C4 (Web Text))

Max Activating Token Index: 326

Text #14

Max Range: 0.7712. Min Range: -0.7712

Max Act: 0.5922. Min Act: -0.0001

Data Index: 931801 (C4 (Web Text))

Max Activating Token Index: 822

Text #15

Max Range: 0.7712. Min Range: -0.7712

Max Act: 0.5701. Min Act: -0.0000

Data Index: 417030 (C4 (Web Text))

Max Activating Token Index: 838

Text #16

Max Range: 0.7712. Min Range: -0.7712

Max Act: 0.5856. Min Act: -0.0000

Data Index: 922889 (C4 (Web Text))

Max Activating Token Index: 694

Text #17

Max Range: 0.7712. Min Range: -0.7712

Max Act: 0.5838. Min Act: -0.0000

Data Index: 163549 (C4 (Web Text))

Max Activating Token Index: 327

Text #18

Max Range: 0.7712. Min Range: -0.7712

Max Act: 0.5901. Min Act: -0.0000

Data Index: 199480 (C4 (Web Text))

Max Activating Token Index: 755

Text #19

Max Range: 0.7712. Min Range: -0.7712

Max Act: 0.5678. Min Act: -0.0000

Data Index: 529617 (C4 (Web Text))

Max Activating Token Index: 956