Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4003 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.7505. Min Range: -0.7505

Max Act: 0.7208. Min Act: -0.0000

Data Index: 1430911 (Python Code)

Max Activating Token Index: 425

Text #1

Max Range: 0.7505. Min Range: -0.7505

Max Act: 0.7505. Min Act: -0.0000

Data Index: 1553822 (Python Code)

Max Activating Token Index: 479

Text #2

Max Range: 0.7505. Min Range: -0.7505

Max Act: 0.7013. Min Act: -0.0000

Data Index: 1486380 (Python Code)

Max Activating Token Index: 86

Text #3

Max Range: 0.7505. Min Range: -0.7505

Max Act: 0.6726. Min Act: -0.0000

Data Index: 1414127 (Python Code)

Max Activating Token Index: 556

Text #4

Max Range: 0.7505. Min Range: -0.7505

Max Act: 0.6952. Min Act: -0.0000

Data Index: 1629494 (Python Code)

Max Activating Token Index: 199

Text #5

Max Range: 0.7505. Min Range: -0.7505

Max Act: 0.6311. Min Act: -0.0000

Data Index: 1583974 (Python Code)

Max Activating Token Index: 420

Text #6

Max Range: 0.7505. Min Range: -0.7505

Max Act: 0.6214. Min Act: -0.0000

Data Index: 1627892 (Python Code)

Max Activating Token Index: 596

Text #7

Max Range: 0.7505. Min Range: -0.7505

Max Act: 0.6417. Min Act: -0.0000

Data Index: 1636060 (Python Code)

Max Activating Token Index: 230

Text #8

Max Range: 0.7505. Min Range: -0.7505

Max Act: 0.6160. Min Act: -0.0000

Data Index: 1464878 (Python Code)

Max Activating Token Index: 98

Text #9

Max Range: 0.7505. Min Range: -0.7505

Max Act: 0.5566. Min Act: -0.0000

Data Index: 1546748 (Python Code)

Max Activating Token Index: 141

Text #10

Max Range: 0.7505. Min Range: -0.7505

Max Act: 0.5730. Min Act: -0.0000

Data Index: 1543506 (Python Code)

Max Activating Token Index: 489

Text #11

Max Range: 0.7505. Min Range: -0.7505

Max Act: 0.5807. Min Act: -0.0000

Data Index: 1648588 (Python Code)

Max Activating Token Index: 113

Text #12

Max Range: 0.7505. Min Range: -0.7505

Max Act: 0.5235. Min Act: -0.0000

Data Index: 1501721 (Python Code)

Max Activating Token Index: 426

Text #13

Max Range: 0.7505. Min Range: -0.7505

Max Act: 0.5811. Min Act: -0.0000

Data Index: 1547637 (Python Code)

Max Activating Token Index: 608

Text #14

Max Range: 0.7505. Min Range: -0.7505

Max Act: 0.5518. Min Act: -0.0000

Data Index: 1442827 (Python Code)

Max Activating Token Index: 100

Text #15

Max Range: 0.7505. Min Range: -0.7505

Max Act: 0.5435. Min Act: -0.0000

Data Index: 1560525 (Python Code)

Max Activating Token Index: 452

Text #16

Max Range: 0.7505. Min Range: -0.7505

Max Act: 0.5491. Min Act: -0.0000

Data Index: 1371946 (Python Code)

Max Activating Token Index: 246

Text #17

Max Range: 0.7505. Min Range: -0.7505

Max Act: 0.5439. Min Act: -0.0000

Data Index: 1510607 (Python Code)

Max Activating Token Index: 379

Text #18

Max Range: 0.7505. Min Range: -0.7505

Max Act: 0.5540. Min Act: -0.0000

Data Index: 1601544 (Python Code)

Max Activating Token Index: 356

Text #19

Max Range: 0.7505. Min Range: -0.7505

Max Act: 0.5478. Min Act: -0.0000

Data Index: 1524608 (Python Code)

Max Activating Token Index: 709