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

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

Neuron 1704 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6940. Min Range: -1.6940

Max Act: 1.6089. Min Act: -0.0002

Data Index: 261278 (C4 (Web Text))

Max Activating Token Index: 710

Text #1

Max Range: 1.6940. Min Range: -1.6940

Max Act: 1.6940. Min Act: -0.0002

Data Index: 400186 (C4 (Web Text))

Max Activating Token Index: 696

Text #2

Max Range: 1.6940. Min Range: -1.6940

Max Act: 1.5783. Min Act: -0.0001

Data Index: 1024730 (C4 (Web Text))

Max Activating Token Index: 520

Text #3

Max Range: 1.6940. Min Range: -1.6940

Max Act: 1.6663. Min Act: -0.0001

Data Index: 406030 (C4 (Web Text))

Max Activating Token Index: 656

Text #4

Max Range: 1.6940. Min Range: -1.6940

Max Act: 1.6677. Min Act: -0.0001

Data Index: 232810 (C4 (Web Text))

Max Activating Token Index: 385

Text #5

Max Range: 1.6940. Min Range: -1.6940

Max Act: 1.6152. Min Act: -0.0001

Data Index: 965548 (C4 (Web Text))

Max Activating Token Index: 502

Text #6

Max Range: 1.6940. Min Range: -1.6940

Max Act: 1.5445. Min Act: -0.0001

Data Index: 895901 (C4 (Web Text))

Max Activating Token Index: 474

Text #7

Max Range: 1.6940. Min Range: -1.6940

Max Act: 1.5434. Min Act: -0.0001

Data Index: 768352 (C4 (Web Text))

Max Activating Token Index: 606

Text #8

Max Range: 1.6940. Min Range: -1.6940

Max Act: 1.6022. Min Act: -0.0001

Data Index: 866329 (C4 (Web Text))

Max Activating Token Index: 567

Text #9

Max Range: 1.6940. Min Range: -1.6940

Max Act: 1.5396. Min Act: -0.0001

Data Index: 1341800 (C4 (Web Text))

Max Activating Token Index: 611

Text #10

Max Range: 1.6940. Min Range: -1.6940

Max Act: 1.5288. Min Act: -0.0002

Data Index: 523725 (C4 (Web Text))

Max Activating Token Index: 705

Text #11

Max Range: 1.6940. Min Range: -1.6940

Max Act: 1.6374. Min Act: -0.0001

Data Index: 931372 (C4 (Web Text))

Max Activating Token Index: 718

Text #12

Max Range: 1.6940. Min Range: -1.6940

Max Act: 1.5137. Min Act: -0.0001

Data Index: 1009395 (C4 (Web Text))

Max Activating Token Index: 524

Text #13

Max Range: 1.6940. Min Range: -1.6940

Max Act: 1.5101. Min Act: -0.0001

Data Index: 1001748 (C4 (Web Text))

Max Activating Token Index: 466

Text #14

Max Range: 1.6940. Min Range: -1.6940

Max Act: 1.6761. Min Act: -0.0002

Data Index: 464464 (C4 (Web Text))

Max Activating Token Index: 714

Text #15

Max Range: 1.6940. Min Range: -1.6940

Max Act: 1.4524. Min Act: -0.0001

Data Index: 624981 (C4 (Web Text))

Max Activating Token Index: 352

Text #16

Max Range: 1.6940. Min Range: -1.6940

Max Act: 1.5385. Min Act: -0.0002

Data Index: 560526 (C4 (Web Text))

Max Activating Token Index: 428

Text #17

Max Range: 1.6940. Min Range: -1.6940

Max Act: 1.4073. Min Act: -0.0002

Data Index: 847029 (C4 (Web Text))

Max Activating Token Index: 504

Text #18

Max Range: 1.6940. Min Range: -1.6940

Max Act: 1.4862. Min Act: -0.0002

Data Index: 999423 (C4 (Web Text))

Max Activating Token Index: 476

Text #19

Max Range: 1.6940. Min Range: -1.6940

Max Act: 1.4826. Min Act: -0.0001

Data Index: 654474 (C4 (Web Text))

Max Activating Token Index: 394