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

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

Neuron 547 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8534. Min Range: -2.8534

Max Act: 2.8534. Min Act: -0.0000

Data Index: 1627018 (Python Code)

Max Activating Token Index: 630

Text #1

Max Range: 2.8534. Min Range: -2.8534

Max Act: 2.7261. Min Act: -0.0000

Data Index: 1455962 (Python Code)

Max Activating Token Index: 958

Text #2

Max Range: 2.8534. Min Range: -2.8534

Max Act: 2.6609. Min Act: -0.0000

Data Index: 1413895 (Python Code)

Max Activating Token Index: 573

Text #3

Max Range: 2.8534. Min Range: -2.8534

Max Act: 2.6103. Min Act: -0.0000

Data Index: 1614749 (Python Code)

Max Activating Token Index: 344

Text #4

Max Range: 2.8534. Min Range: -2.8534

Max Act: 2.4287. Min Act: -0.0000

Data Index: 1438654 (Python Code)

Max Activating Token Index: 471

Text #5

Max Range: 2.8534. Min Range: -2.8534

Max Act: 2.4129. Min Act: -0.0000

Data Index: 1610045 (Python Code)

Max Activating Token Index: 420

Text #6

Max Range: 2.8534. Min Range: -2.8534

Max Act: 2.5153. Min Act: -0.0000

Data Index: 1594064 (Python Code)

Max Activating Token Index: 638

Text #7

Max Range: 2.8534. Min Range: -2.8534

Max Act: 2.4537. Min Act: -0.0000

Data Index: 1439345 (Python Code)

Max Activating Token Index: 262

Text #8

Max Range: 2.8534. Min Range: -2.8534

Max Act: 2.3980. Min Act: -0.0000

Data Index: 1515375 (Python Code)

Max Activating Token Index: 965

Text #9

Max Range: 2.8534. Min Range: -2.8534

Max Act: 2.3996. Min Act: -0.0000

Data Index: 1406153 (Python Code)

Max Activating Token Index: 729

Text #10

Max Range: 2.8534. Min Range: -2.8534

Max Act: 2.3228. Min Act: -0.0000

Data Index: 1564316 (Python Code)

Max Activating Token Index: 372

Text #11

Max Range: 2.8534. Min Range: -2.8534

Max Act: 2.3409. Min Act: -0.0000

Data Index: 1578036 (Python Code)

Max Activating Token Index: 843

Text #12

Max Range: 2.8534. Min Range: -2.8534

Max Act: 2.4481. Min Act: -0.0000

Data Index: 1386811 (Python Code)

Max Activating Token Index: 438

Text #13

Max Range: 2.8534. Min Range: -2.8534

Max Act: 2.1673. Min Act: -0.0000

Data Index: 1392942 (Python Code)

Max Activating Token Index: 241

Text #14

Max Range: 2.8534. Min Range: -2.8534

Max Act: 2.3877. Min Act: -0.0000

Data Index: 1390690 (Python Code)

Max Activating Token Index: 734

Text #15

Max Range: 2.8534. Min Range: -2.8534

Max Act: 2.2466. Min Act: -0.0000

Data Index: 1490292 (Python Code)

Max Activating Token Index: 867

Text #16

Max Range: 2.8534. Min Range: -2.8534

Max Act: 2.2087. Min Act: -0.0000

Data Index: 1383561 (Python Code)

Max Activating Token Index: 739

Text #17

Max Range: 2.8534. Min Range: -2.8534

Max Act: 2.3256. Min Act: -0.0000

Data Index: 1459279 (Python Code)

Max Activating Token Index: 205

Text #18

Max Range: 2.8534. Min Range: -2.8534

Max Act: 1.9754. Min Act: -0.0000

Data Index: 1388730 (Python Code)

Max Activating Token Index: 23

Text #19

Max Range: 2.8534. Min Range: -2.8534

Max Act: 2.4190. Min Act: -0.0000

Data Index: 1611884 (Python Code)

Max Activating Token Index: 714