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

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

Neuron 4738 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7558. Min Range: -0.7558

Max Act: 0.7558. Min Act: -0.0000

Data Index: 407617 (C4 (Web Text))

Max Activating Token Index: 900

Text #1

Max Range: 0.7558. Min Range: -0.7558

Max Act: 0.6046. Min Act: -0.0000

Data Index: 630072 (C4 (Web Text))

Max Activating Token Index: 544

Text #2

Max Range: 0.7558. Min Range: -0.7558

Max Act: 0.5841. Min Act: -0.0000

Data Index: 1348807 (C4 (Web Text))

Max Activating Token Index: 713

Text #3

Max Range: 0.7558. Min Range: -0.7558

Max Act: 0.5596. Min Act: -0.0000

Data Index: 628024 (C4 (Web Text))

Max Activating Token Index: 726

Text #4

Max Range: 0.7558. Min Range: -0.7558

Max Act: 0.5477. Min Act: -0.0000

Data Index: 525193 (C4 (Web Text))

Max Activating Token Index: 806

Text #5

Max Range: 0.7558. Min Range: -0.7558

Max Act: 0.5862. Min Act: -0.0000

Data Index: 51768 (C4 (Web Text))

Max Activating Token Index: 527

Text #6

Max Range: 0.7558. Min Range: -0.7558

Max Act: 0.5492. Min Act: -0.0000

Data Index: 148437 (C4 (Web Text))

Max Activating Token Index: 1009

Text #7

Max Range: 0.7558. Min Range: -0.7558

Max Act: 0.5197. Min Act: -0.0000

Data Index: 1299197 (C4 (Web Text))

Max Activating Token Index: 824

Text #8

Max Range: 0.7558. Min Range: -0.7558

Max Act: 0.5367. Min Act: -0.0000

Data Index: 1089876 (C4 (Web Text))

Max Activating Token Index: 77

Text #9

Max Range: 0.7558. Min Range: -0.7558

Max Act: 0.5413. Min Act: -0.0000

Data Index: 523669 (C4 (Web Text))

Max Activating Token Index: 129

Text #10

Max Range: 0.7558. Min Range: -0.7558

Max Act: 0.5140. Min Act: -0.0000

Data Index: 596007 (C4 (Web Text))

Max Activating Token Index: 74

Text #11

Max Range: 0.7558. Min Range: -0.7558

Max Act: 0.4937. Min Act: -0.0000

Data Index: 961073 (C4 (Web Text))

Max Activating Token Index: 414

Text #12

Max Range: 0.7558. Min Range: -0.7558

Max Act: 0.5011. Min Act: -0.0000

Data Index: 867168 (C4 (Web Text))

Max Activating Token Index: 80

Text #13

Max Range: 0.7558. Min Range: -0.7558

Max Act: 0.5158. Min Act: -0.0000

Data Index: 1093670 (C4 (Web Text))

Max Activating Token Index: 349

Text #14

Max Range: 0.7558. Min Range: -0.7558

Max Act: 0.4996. Min Act: -0.0000

Data Index: 402485 (C4 (Web Text))

Max Activating Token Index: 513

Text #15

Max Range: 0.7558. Min Range: -0.7558

Max Act: 0.4824. Min Act: -0.0000

Data Index: 678594 (C4 (Web Text))

Max Activating Token Index: 310

Text #16

Max Range: 0.7558. Min Range: -0.7558

Max Act: 0.4754. Min Act: -0.0000

Data Index: 882076 (C4 (Web Text))

Max Activating Token Index: 685

Text #17

Max Range: 0.7558. Min Range: -0.7558

Max Act: 0.4762. Min Act: -0.0000

Data Index: 37595 (C4 (Web Text))

Max Activating Token Index: 371

Text #18

Max Range: 0.7558. Min Range: -0.7558

Max Act: 0.4983. Min Act: -0.0000

Data Index: 816191 (C4 (Web Text))

Max Activating Token Index: 700

Text #19

Max Range: 0.7558. Min Range: -0.7558

Max Act: 0.4929. Min Act: -0.0000

Data Index: 720391 (C4 (Web Text))

Max Activating Token Index: 412