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

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

Neuron 5115 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8410. Min Range: -0.8410

Max Act: 0.8410. Min Act: -0.0000

Data Index: 1169171 (C4 (Web Text))

Max Activating Token Index: 130

Text #1

Max Range: 0.8410. Min Range: -0.8410

Max Act: 0.7369. Min Act: -0.0000

Data Index: 270277 (C4 (Web Text))

Max Activating Token Index: 271

Text #2

Max Range: 0.8410. Min Range: -0.8410

Max Act: 0.7448. Min Act: -0.0000

Data Index: 272872 (C4 (Web Text))

Max Activating Token Index: 363

Text #3

Max Range: 0.8410. Min Range: -0.8410

Max Act: 0.5850. Min Act: -0.0000

Data Index: 727131 (C4 (Web Text))

Max Activating Token Index: 163

Text #4

Max Range: 0.8410. Min Range: -0.8410

Max Act: 0.6666. Min Act: -0.0000

Data Index: 790939 (C4 (Web Text))

Max Activating Token Index: 351

Text #5

Max Range: 0.8410. Min Range: -0.8410

Max Act: 0.6275. Min Act: -0.0000

Data Index: 665141 (C4 (Web Text))

Max Activating Token Index: 491

Text #6

Max Range: 0.8410. Min Range: -0.8410

Max Act: 0.5861. Min Act: -0.0000

Data Index: 456736 (C4 (Web Text))

Max Activating Token Index: 507

Text #7

Max Range: 0.8410. Min Range: -0.8410

Max Act: 0.6492. Min Act: -0.0000

Data Index: 63108 (C4 (Web Text))

Max Activating Token Index: 394

Text #8

Max Range: 0.8410. Min Range: -0.8410

Max Act: 0.6497. Min Act: -0.0000

Data Index: 1190713 (C4 (Web Text))

Max Activating Token Index: 453

Text #9

Max Range: 0.8410. Min Range: -0.8410

Max Act: 0.4525. Min Act: -0.0000

Data Index: 837408 (C4 (Web Text))

Max Activating Token Index: 710

Text #10

Max Range: 0.8410. Min Range: -0.8410

Max Act: 0.4324. Min Act: -0.0000

Data Index: 978213 (C4 (Web Text))

Max Activating Token Index: 761

Text #11

Max Range: 0.8410. Min Range: -0.8410

Max Act: 0.5840. Min Act: -0.0000

Data Index: 196067 (C4 (Web Text))

Max Activating Token Index: 254

Text #12

Max Range: 0.8410. Min Range: -0.8410

Max Act: 0.4700. Min Act: -0.0000

Data Index: 644814 (C4 (Web Text))

Max Activating Token Index: 235

Text #13

Max Range: 0.8410. Min Range: -0.8410

Max Act: 0.5483. Min Act: -0.0000

Data Index: 645045 (C4 (Web Text))

Max Activating Token Index: 722

Text #14

Max Range: 0.8410. Min Range: -0.8410

Max Act: 0.5727. Min Act: -0.0000

Data Index: 738089 (C4 (Web Text))

Max Activating Token Index: 305

Text #15

Max Range: 0.8410. Min Range: -0.8410

Max Act: 0.5365. Min Act: -0.0000

Data Index: 495868 (C4 (Web Text))

Max Activating Token Index: 335

Text #16

Max Range: 0.8410. Min Range: -0.8410

Max Act: 0.5594. Min Act: -0.0000

Data Index: 324891 (C4 (Web Text))

Max Activating Token Index: 342

Text #17

Max Range: 0.8410. Min Range: -0.8410

Max Act: 0.4520. Min Act: -0.0000

Data Index: 1117690 (C4 (Web Text))

Max Activating Token Index: 622

Text #18

Max Range: 0.8410. Min Range: -0.8410

Max Act: 0.4549. Min Act: -0.0000

Data Index: 721728 (C4 (Web Text))

Max Activating Token Index: 141

Text #19

Max Range: 0.8410. Min Range: -0.8410

Max Act: 0.5076. Min Act: -0.0000

Data Index: 170078 (C4 (Web Text))

Max Activating Token Index: 26