Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2496 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.1610. Min Range: -1.1610

Max Act: 1.1610. Min Act: -0.0003

Data Index: 1138804 (C4 (Web Text))

Max Activating Token Index: 230

Text #1

Max Range: 1.1610. Min Range: -1.1610

Max Act: 1.1051. Min Act: -0.0003

Data Index: 971099 (C4 (Web Text))

Max Activating Token Index: 275

Text #2

Max Range: 1.1610. Min Range: -1.1610

Max Act: 1.0309. Min Act: -0.0003

Data Index: 1225087 (C4 (Web Text))

Max Activating Token Index: 468

Text #3

Max Range: 1.1610. Min Range: -1.1610

Max Act: 0.9263. Min Act: -0.0003

Data Index: 150483 (C4 (Web Text))

Max Activating Token Index: 377

Text #4

Max Range: 1.1610. Min Range: -1.1610

Max Act: 0.9063. Min Act: -0.0003

Data Index: 457318 (C4 (Web Text))

Max Activating Token Index: 702

Text #5

Max Range: 1.1610. Min Range: -1.1610

Max Act: 0.8362. Min Act: -0.0003

Data Index: 1120916 (C4 (Web Text))

Max Activating Token Index: 936

Text #6

Max Range: 1.1610. Min Range: -1.1610

Max Act: 0.9450. Min Act: -0.0003

Data Index: 275168 (C4 (Web Text))

Max Activating Token Index: 739

Text #7

Max Range: 1.1610. Min Range: -1.1610

Max Act: 0.9586. Min Act: -0.0003

Data Index: 519823 (C4 (Web Text))

Max Activating Token Index: 441

Text #8

Max Range: 1.1610. Min Range: -1.1610

Max Act: 0.9553. Min Act: -0.0003

Data Index: 42332 (C4 (Web Text))

Max Activating Token Index: 266

Text #9

Max Range: 1.1610. Min Range: -1.1610

Max Act: 0.9982. Min Act: -0.0003

Data Index: 784864 (C4 (Web Text))

Max Activating Token Index: 235

Text #10

Max Range: 1.1610. Min Range: -1.1610

Max Act: 0.8673. Min Act: -0.0003

Data Index: 382574 (C4 (Web Text))

Max Activating Token Index: 469

Text #11

Max Range: 1.1610. Min Range: -1.1610

Max Act: 0.9081. Min Act: -0.0003

Data Index: 1270907 (C4 (Web Text))

Max Activating Token Index: 508

Text #12

Max Range: 1.1610. Min Range: -1.1610

Max Act: 0.7794. Min Act: -0.0003

Data Index: 632784 (C4 (Web Text))

Max Activating Token Index: 836

Text #13

Max Range: 1.1610. Min Range: -1.1610

Max Act: 0.8967. Min Act: -0.0003

Data Index: 1300261 (C4 (Web Text))

Max Activating Token Index: 480

Text #14

Max Range: 1.1610. Min Range: -1.1610

Max Act: 0.9246. Min Act: -0.0003

Data Index: 79871 (C4 (Web Text))

Max Activating Token Index: 959

Text #15

Max Range: 1.1610. Min Range: -1.1610

Max Act: 0.9709. Min Act: -0.0003

Data Index: 611852 (C4 (Web Text))

Max Activating Token Index: 715

Text #16

Max Range: 1.1610. Min Range: -1.1610

Max Act: 0.8518. Min Act: -0.0003

Data Index: 709386 (C4 (Web Text))

Max Activating Token Index: 788

Text #17

Max Range: 1.1610. Min Range: -1.1610

Max Act: 0.8039. Min Act: -0.0003

Data Index: 424057 (C4 (Web Text))

Max Activating Token Index: 138

Text #18

Max Range: 1.1610. Min Range: -1.1610

Max Act: 0.7757. Min Act: -0.0003

Data Index: 464922 (C4 (Web Text))

Max Activating Token Index: 294

Text #19

Max Range: 1.1610. Min Range: -1.1610

Max Act: 0.8114. Min Act: -0.0003

Data Index: 327696 (C4 (Web Text))

Max Activating Token Index: 542