Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1373 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.0029. Min Range: -1.0029

Max Act: 1.0029. Min Act: -0.0000

Data Index: 266916 (C4 (Web Text))

Max Activating Token Index: 589

Text #1

Max Range: 1.0029. Min Range: -1.0029

Max Act: 0.5851. Min Act: -0.0000

Data Index: 679981 (C4 (Web Text))

Max Activating Token Index: 33

Text #2

Max Range: 1.0029. Min Range: -1.0029

Max Act: 0.5709. Min Act: -0.0000

Data Index: 766315 (C4 (Web Text))

Max Activating Token Index: 431

Text #3

Max Range: 1.0029. Min Range: -1.0029

Max Act: 0.5145. Min Act: -0.0000

Data Index: 1181469 (C4 (Web Text))

Max Activating Token Index: 323

Text #4

Max Range: 1.0029. Min Range: -1.0029

Max Act: 0.4930. Min Act: -0.0000

Data Index: 11425 (C4 (Web Text))

Max Activating Token Index: 373

Text #5

Max Range: 1.0029. Min Range: -1.0029

Max Act: 0.4927. Min Act: -0.0000

Data Index: 314444 (C4 (Web Text))

Max Activating Token Index: 141

Text #6

Max Range: 1.0029. Min Range: -1.0029

Max Act: 0.4828. Min Act: -0.0000

Data Index: 769025 (C4 (Web Text))

Max Activating Token Index: 309

Text #7

Max Range: 1.0029. Min Range: -1.0029

Max Act: 0.4872. Min Act: -0.0000

Data Index: 385756 (C4 (Web Text))

Max Activating Token Index: 826

Text #8

Max Range: 1.0029. Min Range: -1.0029

Max Act: 0.4470. Min Act: -0.0000

Data Index: 884427 (C4 (Web Text))

Max Activating Token Index: 43

Text #9

Max Range: 1.0029. Min Range: -1.0029

Max Act: 0.4437. Min Act: -0.0000

Data Index: 922146 (C4 (Web Text))

Max Activating Token Index: 535

Text #10

Max Range: 1.0029. Min Range: -1.0029

Max Act: 0.4432. Min Act: -0.0000

Data Index: 904105 (C4 (Web Text))

Max Activating Token Index: 987

Text #11

Max Range: 1.0029. Min Range: -1.0029

Max Act: 0.4195. Min Act: -0.0000

Data Index: 346618 (C4 (Web Text))

Max Activating Token Index: 655

Text #12

Max Range: 1.0029. Min Range: -1.0029

Max Act: 0.4182. Min Act: -0.0000

Data Index: 961085 (C4 (Web Text))

Max Activating Token Index: 360

Text #13

Max Range: 1.0029. Min Range: -1.0029

Max Act: 0.4099. Min Act: -0.0000

Data Index: 1148852 (C4 (Web Text))

Max Activating Token Index: 545

Text #14

Max Range: 1.0029. Min Range: -1.0029

Max Act: 0.3998. Min Act: 0.0000

Data Index: 929916 (C4 (Web Text))

Max Activating Token Index: 872

Text #15

Max Range: 1.0029. Min Range: -1.0029

Max Act: 0.4120. Min Act: -0.0000

Data Index: 838001 (C4 (Web Text))

Max Activating Token Index: 88

Text #16

Max Range: 1.0029. Min Range: -1.0029

Max Act: 0.4254. Min Act: -0.0000

Data Index: 979137 (C4 (Web Text))

Max Activating Token Index: 990

Text #17

Max Range: 1.0029. Min Range: -1.0029

Max Act: 0.4088. Min Act: -0.0000

Data Index: 928604 (C4 (Web Text))

Max Activating Token Index: 500

Text #18

Max Range: 1.0029. Min Range: -1.0029

Max Act: 0.4177. Min Act: -0.0000

Data Index: 23767 (C4 (Web Text))

Max Activating Token Index: 604

Text #19

Max Range: 1.0029. Min Range: -1.0029

Max Act: 0.3993. Min Act: -0.0000

Data Index: 93607 (C4 (Web Text))

Max Activating Token Index: 866