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

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

Neuron 3584 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: 3.2208. Min Range: -3.2208

Max Act: 3.2208. Min Act: -0.0000

Data Index: 668482 (C4 (Web Text))

Max Activating Token Index: 350

Text #1

Max Range: 3.2208. Min Range: -3.2208

Max Act: 1.9008. Min Act: -0.0000

Data Index: 290318 (C4 (Web Text))

Max Activating Token Index: 1014

Text #2

Max Range: 3.2208. Min Range: -3.2208

Max Act: 2.0975. Min Act: -0.0000

Data Index: 377614 (C4 (Web Text))

Max Activating Token Index: 459

Text #3

Max Range: 3.2208. Min Range: -3.2208

Max Act: 1.5618. Min Act: -0.0000

Data Index: 1322504 (C4 (Web Text))

Max Activating Token Index: 613

Text #4

Max Range: 3.2208. Min Range: -3.2208

Max Act: 1.4821. Min Act: -0.0000

Data Index: 737002 (C4 (Web Text))

Max Activating Token Index: 450

Text #5

Max Range: 3.2208. Min Range: -3.2208

Max Act: 1.2279. Min Act: 0.0000

Data Index: 790284 (C4 (Web Text))

Max Activating Token Index: 28

Text #6

Max Range: 3.2208. Min Range: -3.2208

Max Act: 1.2418. Min Act: -0.0000

Data Index: 888408 (C4 (Web Text))

Max Activating Token Index: 228

Text #7

Max Range: 3.2208. Min Range: -3.2208

Max Act: 0.9249. Min Act: -0.0000

Data Index: 1456244 (Python Code)

Max Activating Token Index: 154

Text #8

Max Range: 3.2208. Min Range: -3.2208

Max Act: 0.8617. Min Act: -0.0000

Data Index: 1163085 (C4 (Web Text))

Max Activating Token Index: 704

Text #9

Max Range: 3.2208. Min Range: -3.2208

Max Act: 0.9977. Min Act: -0.0000

Data Index: 148906 (C4 (Web Text))

Max Activating Token Index: 277

Text #10

Max Range: 3.2208. Min Range: -3.2208

Max Act: 0.8238. Min Act: -0.0000

Data Index: 863413 (C4 (Web Text))

Max Activating Token Index: 283

Text #11

Max Range: 3.2208. Min Range: -3.2208

Max Act: 0.8924. Min Act: -0.0000

Data Index: 931916 (C4 (Web Text))

Max Activating Token Index: 386

Text #12

Max Range: 3.2208. Min Range: -3.2208

Max Act: 0.7821. Min Act: -0.0000

Data Index: 325698 (C4 (Web Text))

Max Activating Token Index: 748

Text #13

Max Range: 3.2208. Min Range: -3.2208

Max Act: 0.8156. Min Act: -0.0000

Data Index: 1062778 (C4 (Web Text))

Max Activating Token Index: 454

Text #14

Max Range: 3.2208. Min Range: -3.2208

Max Act: 0.7532. Min Act: -0.0000

Data Index: 804516 (C4 (Web Text))

Max Activating Token Index: 172

Text #15

Max Range: 3.2208. Min Range: -3.2208

Max Act: 0.5859. Min Act: -0.0001

Data Index: 225557 (C4 (Web Text))

Max Activating Token Index: 850

Text #16

Max Range: 3.2208. Min Range: -3.2208

Max Act: 0.7886. Min Act: -0.0000

Data Index: 740627 (C4 (Web Text))

Max Activating Token Index: 663

Text #17

Max Range: 3.2208. Min Range: -3.2208

Max Act: 0.6138. Min Act: -0.0000

Data Index: 1553342 (Python Code)

Max Activating Token Index: 658

Text #18

Max Range: 3.2208. Min Range: -3.2208

Max Act: 0.6417. Min Act: -0.0000

Data Index: 180045 (C4 (Web Text))

Max Activating Token Index: 231

Text #19

Max Range: 3.2208. Min Range: -3.2208

Max Act: 0.6808. Min Act: -0.0000

Data Index: 134659 (C4 (Web Text))

Max Activating Token Index: 236