Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1540 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.0976. Min Range: -2.0976

Max Act: 2.0903. Min Act: -0.0001

Data Index: 1630966 (Python Code)

Max Activating Token Index: 586

Text #1

Max Range: 2.0976. Min Range: -2.0976

Max Act: 2.0976. Min Act: -0.0000

Data Index: 1530126 (Python Code)

Max Activating Token Index: 225

Text #2

Max Range: 2.0976. Min Range: -2.0976

Max Act: 1.9903. Min Act: -0.0001

Data Index: 1413887 (Python Code)

Max Activating Token Index: 193

Text #3

Max Range: 2.0976. Min Range: -2.0976

Max Act: 2.0372. Min Act: -0.0000

Data Index: 1553585 (Python Code)

Max Activating Token Index: 202

Text #4

Max Range: 2.0976. Min Range: -2.0976

Max Act: 1.9571. Min Act: -0.0001

Data Index: 1499971 (Python Code)

Max Activating Token Index: 162

Text #5

Max Range: 2.0976. Min Range: -2.0976

Max Act: 1.9458. Min Act: -0.0000

Data Index: 1447676 (Python Code)

Max Activating Token Index: 130

Text #6

Max Range: 2.0976. Min Range: -2.0976

Max Act: 1.8370. Min Act: -0.0000

Data Index: 1367240 (Python Code)

Max Activating Token Index: 176

Text #7

Max Range: 2.0976. Min Range: -2.0976

Max Act: 1.6703. Min Act: -0.0000

Data Index: 1441427 (Python Code)

Max Activating Token Index: 247

Text #8

Max Range: 2.0976. Min Range: -2.0976

Max Act: 1.6431. Min Act: -0.0000

Data Index: 1032300 (C4 (Web Text))

Max Activating Token Index: 753

Text #9

Max Range: 2.0976. Min Range: -2.0976

Max Act: 1.5867. Min Act: -0.0000

Data Index: 1540201 (Python Code)

Max Activating Token Index: 284

Text #10

Max Range: 2.0976. Min Range: -2.0976

Max Act: 1.5712. Min Act: -0.0001

Data Index: 1652005 (Python Code)

Max Activating Token Index: 620

Text #11

Max Range: 2.0976. Min Range: -2.0976

Max Act: 1.6868. Min Act: -0.0001

Data Index: 1413359 (Python Code)

Max Activating Token Index: 673

Text #12

Max Range: 2.0976. Min Range: -2.0976

Max Act: 1.5430. Min Act: -0.0000

Data Index: 1427491 (Python Code)

Max Activating Token Index: 988

Text #13

Max Range: 2.0976. Min Range: -2.0976

Max Act: 1.6211. Min Act: -0.0000

Data Index: 1500417 (Python Code)

Max Activating Token Index: 22

Text #14

Max Range: 2.0976. Min Range: -2.0976

Max Act: 1.7053. Min Act: -0.0000

Data Index: 1446938 (Python Code)

Max Activating Token Index: 253

Text #15

Max Range: 2.0976. Min Range: -2.0976

Max Act: 1.6144. Min Act: -0.0001

Data Index: 1480181 (Python Code)

Max Activating Token Index: 162

Text #16

Max Range: 2.0976. Min Range: -2.0976

Max Act: 1.2875. Min Act: -0.0000

Data Index: 989024 (C4 (Web Text))

Max Activating Token Index: 250

Text #17

Max Range: 2.0976. Min Range: -2.0976

Max Act: 1.6091. Min Act: -0.0000

Data Index: 1484592 (Python Code)

Max Activating Token Index: 577

Text #18

Max Range: 2.0976. Min Range: -2.0976

Max Act: 1.5077. Min Act: -0.0000

Data Index: 209801 (C4 (Web Text))

Max Activating Token Index: 872

Text #19

Max Range: 2.0976. Min Range: -2.0976

Max Act: 1.5723. Min Act: -0.0001

Data Index: 1566272 (Python Code)

Max Activating Token Index: 405