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

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

Neuron 4330 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9922. Min Range: -2.9922

Max Act: 2.9922. Min Act: -0.0000

Data Index: 991686 (C4 (Web Text))

Max Activating Token Index: 205

Text #1

Max Range: 2.9922. Min Range: -2.9922

Max Act: 2.4449. Min Act: -0.0000

Data Index: 1020695 (C4 (Web Text))

Max Activating Token Index: 488

Text #2

Max Range: 2.9922. Min Range: -2.9922

Max Act: 2.5734. Min Act: -0.0000

Data Index: 1118306 (C4 (Web Text))

Max Activating Token Index: 371

Text #3

Max Range: 2.9922. Min Range: -2.9922

Max Act: 2.1968. Min Act: -0.0000

Data Index: 1332182 (C4 (Web Text))

Max Activating Token Index: 998

Text #4

Max Range: 2.9922. Min Range: -2.9922

Max Act: 1.9789. Min Act: -0.0000

Data Index: 213723 (C4 (Web Text))

Max Activating Token Index: 25

Text #5

Max Range: 2.9922. Min Range: -2.9922

Max Act: 1.7088. Min Act: -0.0000

Data Index: 1170684 (C4 (Web Text))

Max Activating Token Index: 239

Text #6

Max Range: 2.9922. Min Range: -2.9922

Max Act: 1.9639. Min Act: -0.0000

Data Index: 1182306 (C4 (Web Text))

Max Activating Token Index: 121

Text #7

Max Range: 2.9922. Min Range: -2.9922

Max Act: 2.0631. Min Act: -0.0000

Data Index: 749029 (C4 (Web Text))

Max Activating Token Index: 238

Text #8

Max Range: 2.9922. Min Range: -2.9922

Max Act: 2.0470. Min Act: -0.0000

Data Index: 977570 (C4 (Web Text))

Max Activating Token Index: 130

Text #9

Max Range: 2.9922. Min Range: -2.9922

Max Act: 1.9685. Min Act: -0.0000

Data Index: 79224 (C4 (Web Text))

Max Activating Token Index: 482

Text #10

Max Range: 2.9922. Min Range: -2.9922

Max Act: 1.7376. Min Act: -0.0000

Data Index: 1287281 (C4 (Web Text))

Max Activating Token Index: 610

Text #11

Max Range: 2.9922. Min Range: -2.9922

Max Act: 1.9274. Min Act: -0.0000

Data Index: 221064 (C4 (Web Text))

Max Activating Token Index: 132

Text #12

Max Range: 2.9922. Min Range: -2.9922

Max Act: 1.6106. Min Act: -0.0000

Data Index: 569013 (C4 (Web Text))

Max Activating Token Index: 261

Text #13

Max Range: 2.9922. Min Range: -2.9922

Max Act: 1.7240. Min Act: -0.0000

Data Index: 1138766 (C4 (Web Text))

Max Activating Token Index: 484

Text #14

Max Range: 2.9922. Min Range: -2.9922

Max Act: 1.7968. Min Act: -0.0000

Data Index: 1337367 (C4 (Web Text))

Max Activating Token Index: 419

Text #15

Max Range: 2.9922. Min Range: -2.9922

Max Act: 1.9103. Min Act: -0.0000

Data Index: 549519 (C4 (Web Text))

Max Activating Token Index: 739

Text #16

Max Range: 2.9922. Min Range: -2.9922

Max Act: 1.7915. Min Act: -0.0000

Data Index: 1002421 (C4 (Web Text))

Max Activating Token Index: 242

Text #17

Max Range: 2.9922. Min Range: -2.9922

Max Act: 1.6902. Min Act: -0.0000

Data Index: 167494 (C4 (Web Text))

Max Activating Token Index: 182

Text #18

Max Range: 2.9922. Min Range: -2.9922

Max Act: 1.8942. Min Act: -0.0000

Data Index: 338376 (C4 (Web Text))

Max Activating Token Index: 706

Text #19

Max Range: 2.9922. Min Range: -2.9922

Max Act: 1.7368. Min Act: -0.0000

Data Index: 304112 (C4 (Web Text))

Max Activating Token Index: 288