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

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

Neuron 160 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4841. Min Range: -1.4841

Max Act: 1.3803. Min Act: -0.0001

Data Index: 22997 (C4 (Web Text))

Max Activating Token Index: 408

Text #1

Max Range: 1.4841. Min Range: -1.4841

Max Act: 1.3139. Min Act: -0.0001

Data Index: 499228 (C4 (Web Text))

Max Activating Token Index: 108

Text #2

Max Range: 1.4841. Min Range: -1.4841

Max Act: 1.2336. Min Act: -0.0001

Data Index: 128727 (C4 (Web Text))

Max Activating Token Index: 601

Text #3

Max Range: 1.4841. Min Range: -1.4841

Max Act: 1.4841. Min Act: -0.0001

Data Index: 318226 (C4 (Web Text))

Max Activating Token Index: 647

Text #4

Max Range: 1.4841. Min Range: -1.4841

Max Act: 1.3413. Min Act: -0.0001

Data Index: 340842 (C4 (Web Text))

Max Activating Token Index: 247

Text #5

Max Range: 1.4841. Min Range: -1.4841

Max Act: 1.2226. Min Act: -0.0001

Data Index: 67789 (C4 (Web Text))

Max Activating Token Index: 333

Text #6

Max Range: 1.4841. Min Range: -1.4841

Max Act: 1.2124. Min Act: -0.0001

Data Index: 260952 (C4 (Web Text))

Max Activating Token Index: 16

Text #7

Max Range: 1.4841. Min Range: -1.4841

Max Act: 1.1512. Min Act: -0.0001

Data Index: 198872 (C4 (Web Text))

Max Activating Token Index: 483

Text #8

Max Range: 1.4841. Min Range: -1.4841

Max Act: 1.1454. Min Act: -0.0001

Data Index: 824196 (C4 (Web Text))

Max Activating Token Index: 11

Text #9

Max Range: 1.4841. Min Range: -1.4841

Max Act: 1.2434. Min Act: -0.0001

Data Index: 334328 (C4 (Web Text))

Max Activating Token Index: 685

Text #10

Max Range: 1.4841. Min Range: -1.4841

Max Act: 1.1816. Min Act: -0.0001

Data Index: 166639 (C4 (Web Text))

Max Activating Token Index: 370

Text #11

Max Range: 1.4841. Min Range: -1.4841

Max Act: 1.1624. Min Act: -0.0001

Data Index: 1021989 (C4 (Web Text))

Max Activating Token Index: 579

Text #12

Max Range: 1.4841. Min Range: -1.4841

Max Act: 0.9887. Min Act: -0.0001

Data Index: 782260 (C4 (Web Text))

Max Activating Token Index: 656

Text #13

Max Range: 1.4841. Min Range: -1.4841

Max Act: 1.1292. Min Act: -0.0001

Data Index: 683999 (C4 (Web Text))

Max Activating Token Index: 403

Text #14

Max Range: 1.4841. Min Range: -1.4841

Max Act: 1.0892. Min Act: -0.0001

Data Index: 1100629 (C4 (Web Text))

Max Activating Token Index: 730

Text #15

Max Range: 1.4841. Min Range: -1.4841

Max Act: 0.9978. Min Act: -0.0001

Data Index: 458746 (C4 (Web Text))

Max Activating Token Index: 476

Text #16

Max Range: 1.4841. Min Range: -1.4841

Max Act: 0.9389. Min Act: -0.0001

Data Index: 224085 (C4 (Web Text))

Max Activating Token Index: 56

Text #17

Max Range: 1.4841. Min Range: -1.4841

Max Act: 1.0681. Min Act: -0.0001

Data Index: 1220500 (C4 (Web Text))

Max Activating Token Index: 689

Text #18

Max Range: 1.4841. Min Range: -1.4841

Max Act: 1.0109. Min Act: -0.0001

Data Index: 183063 (C4 (Web Text))

Max Activating Token Index: 314

Text #19

Max Range: 1.4841. Min Range: -1.4841

Max Act: 0.9755. Min Act: -0.0001

Data Index: 683985 (C4 (Web Text))

Max Activating Token Index: 832