Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 79 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0351. Min Act: -0.0004

Data Index: 703 (C4 (Web Text))

Max Activating Token Index: 1

Text #1

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0351. Min Act: -0.0004

Data Index: 1601830 (Python Code)

Max Activating Token Index: 1

Text #2

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0351. Min Act: -0.0003

Data Index: 1499651 (Python Code)

Max Activating Token Index: 1

Text #3

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0351. Min Act: -0.0003

Data Index: 1381130 (Python Code)

Max Activating Token Index: 1

Text #4

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0351. Min Act: -0.0003

Data Index: 1539956 (Python Code)

Max Activating Token Index: 1

Text #5

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0351. Min Act: -0.0004

Data Index: 1576730 (Python Code)

Max Activating Token Index: 1

Text #6

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0351. Min Act: -0.0003

Data Index: 1394483 (Python Code)

Max Activating Token Index: 1

Text #7

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0351. Min Act: -0.0003

Data Index: 1363868 (Python Code)

Max Activating Token Index: 1

Text #8

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0351. Min Act: -0.0003

Data Index: 1611562 (Python Code)

Max Activating Token Index: 1

Text #9

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0351. Min Act: -0.0003

Data Index: 64611 (C4 (Web Text))

Max Activating Token Index: 1

Text #10

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0351. Min Act: -0.0004

Data Index: 65625 (C4 (Web Text))

Max Activating Token Index: 1

Text #11

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0351. Min Act: -0.0003

Data Index: 27479 (C4 (Web Text))

Max Activating Token Index: 1

Text #12

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0351. Min Act: -0.0003

Data Index: 67362 (C4 (Web Text))

Max Activating Token Index: 1

Text #13

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0351. Min Act: -0.0004

Data Index: 70748 (C4 (Web Text))

Max Activating Token Index: 1

Text #14

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0351. Min Act: -0.0003

Data Index: 76851 (C4 (Web Text))

Max Activating Token Index: 1

Text #15

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0351. Min Act: -0.0004

Data Index: 80207 (C4 (Web Text))

Max Activating Token Index: 1

Text #16

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0351. Min Act: -0.0003

Data Index: 99965 (C4 (Web Text))

Max Activating Token Index: 1

Text #17

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0351. Min Act: -0.0003

Data Index: 2845 (C4 (Web Text))

Max Activating Token Index: 1

Text #18

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0351. Min Act: -0.0004

Data Index: 92348 (C4 (Web Text))

Max Activating Token Index: 1

Text #19

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0351. Min Act: -0.0004

Data Index: 86093 (C4 (Web Text))

Max Activating Token Index: 1