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

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

Neuron 4273 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: 2.0638. Min Range: -2.0638

Max Act: 2.0638. Min Act: -0.0000

Data Index: 189149 (C4 (Web Text))

Max Activating Token Index: 776

Text #1

Max Range: 2.0638. Min Range: -2.0638

Max Act: 1.9219. Min Act: -0.0000

Data Index: 361613 (C4 (Web Text))

Max Activating Token Index: 682

Text #2

Max Range: 2.0638. Min Range: -2.0638

Max Act: 1.8964. Min Act: -0.0000

Data Index: 160908 (C4 (Web Text))

Max Activating Token Index: 420

Text #3

Max Range: 2.0638. Min Range: -2.0638

Max Act: 1.7451. Min Act: -0.0000

Data Index: 747322 (C4 (Web Text))

Max Activating Token Index: 911

Text #4

Max Range: 2.0638. Min Range: -2.0638

Max Act: 1.5815. Min Act: -0.0000

Data Index: 163459 (C4 (Web Text))

Max Activating Token Index: 82

Text #5

Max Range: 2.0638. Min Range: -2.0638

Max Act: 1.6690. Min Act: -0.0000

Data Index: 583975 (C4 (Web Text))

Max Activating Token Index: 589

Text #6

Max Range: 2.0638. Min Range: -2.0638

Max Act: 1.5865. Min Act: -0.0000

Data Index: 847950 (C4 (Web Text))

Max Activating Token Index: 102

Text #7

Max Range: 2.0638. Min Range: -2.0638

Max Act: 1.5640. Min Act: -0.0000

Data Index: 373158 (C4 (Web Text))

Max Activating Token Index: 590

Text #8

Max Range: 2.0638. Min Range: -2.0638

Max Act: 1.5507. Min Act: -0.0000

Data Index: 531900 (C4 (Web Text))

Max Activating Token Index: 52

Text #9

Max Range: 2.0638. Min Range: -2.0638

Max Act: 1.4467. Min Act: -0.0000

Data Index: 133380 (C4 (Web Text))

Max Activating Token Index: 207

Text #10

Max Range: 2.0638. Min Range: -2.0638

Max Act: 1.4269. Min Act: -0.0000

Data Index: 914040 (C4 (Web Text))

Max Activating Token Index: 372

Text #11

Max Range: 2.0638. Min Range: -2.0638

Max Act: 1.4483. Min Act: -0.0000

Data Index: 754130 (C4 (Web Text))

Max Activating Token Index: 290

Text #12

Max Range: 2.0638. Min Range: -2.0638

Max Act: 1.4876. Min Act: -0.0000

Data Index: 361560 (C4 (Web Text))

Max Activating Token Index: 331

Text #13

Max Range: 2.0638. Min Range: -2.0638

Max Act: 1.4782. Min Act: -0.0000

Data Index: 809636 (C4 (Web Text))

Max Activating Token Index: 255

Text #14

Max Range: 2.0638. Min Range: -2.0638

Max Act: 1.4076. Min Act: -0.0000

Data Index: 456326 (C4 (Web Text))

Max Activating Token Index: 282

Text #15

Max Range: 2.0638. Min Range: -2.0638

Max Act: 1.4318. Min Act: -0.0000

Data Index: 1289827 (C4 (Web Text))

Max Activating Token Index: 264

Text #16

Max Range: 2.0638. Min Range: -2.0638

Max Act: 1.4152. Min Act: -0.0000

Data Index: 466655 (C4 (Web Text))

Max Activating Token Index: 868

Text #17

Max Range: 2.0638. Min Range: -2.0638

Max Act: 1.3606. Min Act: -0.0000

Data Index: 731462 (C4 (Web Text))

Max Activating Token Index: 390

Text #18

Max Range: 2.0638. Min Range: -2.0638

Max Act: 1.4430. Min Act: -0.0000

Data Index: 880055 (C4 (Web Text))

Max Activating Token Index: 367

Text #19

Max Range: 2.0638. Min Range: -2.0638

Max Act: 1.3655. Min Act: -0.0000

Data Index: 521739 (C4 (Web Text))

Max Activating Token Index: 1023