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

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

Neuron 739 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9537. Min Range: -0.9537

Max Act: 0.9537. Min Act: -0.0000

Data Index: 240141 (C4 (Web Text))

Max Activating Token Index: 201

Text #1

Max Range: 0.9537. Min Range: -0.9537

Max Act: 0.8122. Min Act: -0.0000

Data Index: 716932 (C4 (Web Text))

Max Activating Token Index: 113

Text #2

Max Range: 0.9537. Min Range: -0.9537

Max Act: 0.8108. Min Act: -0.0000

Data Index: 1064097 (C4 (Web Text))

Max Activating Token Index: 842

Text #3

Max Range: 0.9537. Min Range: -0.9537

Max Act: 0.6086. Min Act: -0.0000

Data Index: 229095 (C4 (Web Text))

Max Activating Token Index: 620

Text #4

Max Range: 0.9537. Min Range: -0.9537

Max Act: 0.5904. Min Act: -0.0000

Data Index: 902908 (C4 (Web Text))

Max Activating Token Index: 680

Text #5

Max Range: 0.9537. Min Range: -0.9537

Max Act: 0.5849. Min Act: -0.0000

Data Index: 123995 (C4 (Web Text))

Max Activating Token Index: 511

Text #6

Max Range: 0.9537. Min Range: -0.9537

Max Act: 0.5784. Min Act: -0.0000

Data Index: 985298 (C4 (Web Text))

Max Activating Token Index: 681

Text #7

Max Range: 0.9537. Min Range: -0.9537

Max Act: 0.5743. Min Act: -0.0000

Data Index: 858264 (C4 (Web Text))

Max Activating Token Index: 341

Text #8

Max Range: 0.9537. Min Range: -0.9537

Max Act: 0.5443. Min Act: -0.0000

Data Index: 440599 (C4 (Web Text))

Max Activating Token Index: 685

Text #9

Max Range: 0.9537. Min Range: -0.9537

Max Act: 0.5474. Min Act: -0.0000

Data Index: 28108 (C4 (Web Text))

Max Activating Token Index: 337

Text #10

Max Range: 0.9537. Min Range: -0.9537

Max Act: 0.5127. Min Act: -0.0000

Data Index: 679003 (C4 (Web Text))

Max Activating Token Index: 504

Text #11

Max Range: 0.9537. Min Range: -0.9537

Max Act: 0.4938. Min Act: -0.0000

Data Index: 1278139 (C4 (Web Text))

Max Activating Token Index: 440

Text #12

Max Range: 0.9537. Min Range: -0.9537

Max Act: 0.4938. Min Act: -0.0000

Data Index: 764773 (C4 (Web Text))

Max Activating Token Index: 481

Text #13

Max Range: 0.9537. Min Range: -0.9537

Max Act: 0.4943. Min Act: -0.0000

Data Index: 371237 (C4 (Web Text))

Max Activating Token Index: 370

Text #14

Max Range: 0.9537. Min Range: -0.9537

Max Act: 0.4750. Min Act: -0.0000

Data Index: 1396499 (Python Code)

Max Activating Token Index: 93

Text #15

Max Range: 0.9537. Min Range: -0.9537

Max Act: 0.4664. Min Act: -0.0000

Data Index: 819147 (C4 (Web Text))

Max Activating Token Index: 567

Text #16

Max Range: 0.9537. Min Range: -0.9537

Max Act: 0.4622. Min Act: -0.0000

Data Index: 867002 (C4 (Web Text))

Max Activating Token Index: 447

Text #17

Max Range: 0.9537. Min Range: -0.9537

Max Act: 0.4770. Min Act: -0.0000

Data Index: 1161713 (C4 (Web Text))

Max Activating Token Index: 80

Text #18

Max Range: 0.9537. Min Range: -0.9537

Max Act: 0.4665. Min Act: -0.0000

Data Index: 979994 (C4 (Web Text))

Max Activating Token Index: 843

Text #19

Max Range: 0.9537. Min Range: -0.9537

Max Act: 0.4604. Min Act: -0.0000

Data Index: 1273814 (C4 (Web Text))

Max Activating Token Index: 212