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

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

Neuron 4184 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: 4.7449. Min Range: -4.7449

Max Act: 4.7449. Min Act: -0.0000

Data Index: 1448028 (Python Code)

Max Activating Token Index: 96

Text #1

Max Range: 4.7449. Min Range: -4.7449

Max Act: 4.4525. Min Act: -0.0000

Data Index: 1532270 (Python Code)

Max Activating Token Index: 474

Text #2

Max Range: 4.7449. Min Range: -4.7449

Max Act: 4.0774. Min Act: -0.0000

Data Index: 1462721 (Python Code)

Max Activating Token Index: 442

Text #3

Max Range: 4.7449. Min Range: -4.7449

Max Act: 4.0627. Min Act: -0.0000

Data Index: 1643715 (Python Code)

Max Activating Token Index: 373

Text #4

Max Range: 4.7449. Min Range: -4.7449

Max Act: 4.0548. Min Act: -0.0000

Data Index: 1600797 (Python Code)

Max Activating Token Index: 732

Text #5

Max Range: 4.7449. Min Range: -4.7449

Max Act: 3.9704. Min Act: -0.0000

Data Index: 1648810 (Python Code)

Max Activating Token Index: 720

Text #6

Max Range: 4.7449. Min Range: -4.7449

Max Act: 3.7210. Min Act: -0.0000

Data Index: 1434793 (Python Code)

Max Activating Token Index: 296

Text #7

Max Range: 4.7449. Min Range: -4.7449

Max Act: 3.8407. Min Act: -0.0000

Data Index: 1377796 (Python Code)

Max Activating Token Index: 144

Text #8

Max Range: 4.7449. Min Range: -4.7449

Max Act: 3.8439. Min Act: -0.0000

Data Index: 1382191 (Python Code)

Max Activating Token Index: 291

Text #9

Max Range: 4.7449. Min Range: -4.7449

Max Act: 3.9515. Min Act: -0.0000

Data Index: 1652550 (Python Code)

Max Activating Token Index: 103

Text #10

Max Range: 4.7449. Min Range: -4.7449

Max Act: 3.8893. Min Act: -0.0000

Data Index: 1372294 (Python Code)

Max Activating Token Index: 480

Text #11

Max Range: 4.7449. Min Range: -4.7449

Max Act: 3.8591. Min Act: -0.0000

Data Index: 1368756 (Python Code)

Max Activating Token Index: 744

Text #12

Max Range: 4.7449. Min Range: -4.7449

Max Act: 3.4302. Min Act: -0.0000

Data Index: 1442152 (Python Code)

Max Activating Token Index: 186

Text #13

Max Range: 4.7449. Min Range: -4.7449

Max Act: 3.8707. Min Act: -0.0000

Data Index: 1384253 (Python Code)

Max Activating Token Index: 392

Text #14

Max Range: 4.7449. Min Range: -4.7449

Max Act: 3.8084. Min Act: -0.0000

Data Index: 1467294 (Python Code)

Max Activating Token Index: 539

Text #15

Max Range: 4.7449. Min Range: -4.7449

Max Act: 3.5895. Min Act: -0.0000

Data Index: 1499075 (Python Code)

Max Activating Token Index: 491

Text #16

Max Range: 4.7449. Min Range: -4.7449

Max Act: 3.7544. Min Act: -0.0000

Data Index: 1498717 (Python Code)

Max Activating Token Index: 629

Text #17

Max Range: 4.7449. Min Range: -4.7449

Max Act: 3.5610. Min Act: -0.0000

Data Index: 1458601 (Python Code)

Max Activating Token Index: 554

Text #18

Max Range: 4.7449. Min Range: -4.7449

Max Act: 3.9078. Min Act: -0.0000

Data Index: 1574082 (Python Code)

Max Activating Token Index: 275

Text #19

Max Range: 4.7449. Min Range: -4.7449

Max Act: 3.3673. Min Act: -0.0000

Data Index: 1433248 (Python Code)

Max Activating Token Index: 100