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

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

Neuron 3284 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7709. Min Range: -3.7709

Max Act: 3.7709. Min Act: -0.0000

Data Index: 445251 (C4 (Web Text))

Max Activating Token Index: 841

Text #1

Max Range: 3.7709. Min Range: -3.7709

Max Act: 3.3115. Min Act: -0.0000

Data Index: 77381 (C4 (Web Text))

Max Activating Token Index: 555

Text #2

Max Range: 3.7709. Min Range: -3.7709

Max Act: 3.2370. Min Act: -0.0000

Data Index: 958298 (C4 (Web Text))

Max Activating Token Index: 799

Text #3

Max Range: 3.7709. Min Range: -3.7709

Max Act: 2.7310. Min Act: -0.0000

Data Index: 697427 (C4 (Web Text))

Max Activating Token Index: 887

Text #4

Max Range: 3.7709. Min Range: -3.7709

Max Act: 2.9114. Min Act: -0.0000

Data Index: 338102 (C4 (Web Text))

Max Activating Token Index: 68

Text #5

Max Range: 3.7709. Min Range: -3.7709

Max Act: 2.8933. Min Act: -0.0000

Data Index: 411267 (C4 (Web Text))

Max Activating Token Index: 358

Text #6

Max Range: 3.7709. Min Range: -3.7709

Max Act: 2.8465. Min Act: -0.0000

Data Index: 289009 (C4 (Web Text))

Max Activating Token Index: 427

Text #7

Max Range: 3.7709. Min Range: -3.7709

Max Act: 2.9055. Min Act: -0.0000

Data Index: 886490 (C4 (Web Text))

Max Activating Token Index: 595

Text #8

Max Range: 3.7709. Min Range: -3.7709

Max Act: 2.7313. Min Act: -0.0000

Data Index: 311838 (C4 (Web Text))

Max Activating Token Index: 473

Text #9

Max Range: 3.7709. Min Range: -3.7709

Max Act: 2.6983. Min Act: -0.0000

Data Index: 495424 (C4 (Web Text))

Max Activating Token Index: 31

Text #10

Max Range: 3.7709. Min Range: -3.7709

Max Act: 2.6910. Min Act: -0.0000

Data Index: 655642 (C4 (Web Text))

Max Activating Token Index: 463

Text #11

Max Range: 3.7709. Min Range: -3.7709

Max Act: 2.6763. Min Act: -0.0000

Data Index: 235644 (C4 (Web Text))

Max Activating Token Index: 99

Text #12

Max Range: 3.7709. Min Range: -3.7709

Max Act: 2.6184. Min Act: -0.0000

Data Index: 31386 (C4 (Web Text))

Max Activating Token Index: 909

Text #13

Max Range: 3.7709. Min Range: -3.7709

Max Act: 2.6135. Min Act: -0.0000

Data Index: 1134192 (C4 (Web Text))

Max Activating Token Index: 371

Text #14

Max Range: 3.7709. Min Range: -3.7709

Max Act: 2.5938. Min Act: -0.0000

Data Index: 706250 (C4 (Web Text))

Max Activating Token Index: 527

Text #15

Max Range: 3.7709. Min Range: -3.7709

Max Act: 2.5523. Min Act: -0.0000

Data Index: 1106280 (C4 (Web Text))

Max Activating Token Index: 372

Text #16

Max Range: 3.7709. Min Range: -3.7709

Max Act: 2.5393. Min Act: -0.0000

Data Index: 844699 (C4 (Web Text))

Max Activating Token Index: 935

Text #17

Max Range: 3.7709. Min Range: -3.7709

Max Act: 2.5498. Min Act: -0.0000

Data Index: 617231 (C4 (Web Text))

Max Activating Token Index: 285

Text #18

Max Range: 3.7709. Min Range: -3.7709

Max Act: 2.5177. Min Act: -0.0000

Data Index: 189484 (C4 (Web Text))

Max Activating Token Index: 668

Text #19

Max Range: 3.7709. Min Range: -3.7709

Max Act: 2.4014. Min Act: -0.0000

Data Index: 372788 (C4 (Web Text))

Max Activating Token Index: 801