Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2718 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0357. Min Act: -0.0002

Data Index: 1360123 (Python Code)

Max Activating Token Index: 1

Text #1

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0357. Min Act: -0.0002

Data Index: 1361485 (Python Code)

Max Activating Token Index: 1

Text #2

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0357. Min Act: -0.0002

Data Index: 1361447 (Python Code)

Max Activating Token Index: 1

Text #3

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0357. Min Act: -0.0002

Data Index: 1360026 (Python Code)

Max Activating Token Index: 1

Text #4

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0357. Min Act: -0.0002

Data Index: 1361450 (Python Code)

Max Activating Token Index: 1

Text #5

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0357. Min Act: -0.0002

Data Index: 1361435 (Python Code)

Max Activating Token Index: 1

Text #6

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0357. Min Act: -0.0002

Data Index: 1361417 (Python Code)

Max Activating Token Index: 1

Text #7

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0357. Min Act: -0.0002

Data Index: 1361385 (Python Code)

Max Activating Token Index: 1

Text #8

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0357. Min Act: -0.0002

Data Index: 1361347 (Python Code)

Max Activating Token Index: 1

Text #9

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0357. Min Act: -0.0002

Data Index: 1360388 (Python Code)

Max Activating Token Index: 1

Text #10

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0357. Min Act: -0.0003

Data Index: 1361197 (Python Code)

Max Activating Token Index: 1

Text #11

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0357. Min Act: -0.0002

Data Index: 1361155 (Python Code)

Max Activating Token Index: 1

Text #12

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0357. Min Act: -0.0002

Data Index: 1360964 (Python Code)

Max Activating Token Index: 1

Text #13

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0357. Min Act: -0.0002

Data Index: 1361758 (Python Code)

Max Activating Token Index: 1

Text #14

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0357. Min Act: -0.0002

Data Index: 1361779 (Python Code)

Max Activating Token Index: 1

Text #15

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0357. Min Act: -0.0002

Data Index: 1360389 (Python Code)

Max Activating Token Index: 1

Text #16

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0357. Min Act: -0.0002

Data Index: 1360560 (Python Code)

Max Activating Token Index: 1

Text #17

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0357. Min Act: -0.0002

Data Index: 1360132 (Python Code)

Max Activating Token Index: 1

Text #18

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0357. Min Act: -0.0002

Data Index: 1360107 (Python Code)

Max Activating Token Index: 1

Text #19

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0357. Min Act: -0.0002

Data Index: 1360853 (Python Code)

Max Activating Token Index: 1