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

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

Neuron 371 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6123. Min Range: -0.6123

Max Act: 0.6123. Min Act: -0.0001

Data Index: 1068158 (C4 (Web Text))

Max Activating Token Index: 398

Text #1

Max Range: 0.6123. Min Range: -0.6123

Max Act: 0.5932. Min Act: -0.0001

Data Index: 133988 (C4 (Web Text))

Max Activating Token Index: 531

Text #2

Max Range: 0.6123. Min Range: -0.6123

Max Act: 0.5913. Min Act: -0.0002

Data Index: 873105 (C4 (Web Text))

Max Activating Token Index: 35

Text #3

Max Range: 0.6123. Min Range: -0.6123

Max Act: 0.5576. Min Act: -0.0001

Data Index: 1424143 (Python Code)

Max Activating Token Index: 957

Text #4

Max Range: 0.6123. Min Range: -0.6123

Max Act: 0.5641. Min Act: -0.0001

Data Index: 1411975 (Python Code)

Max Activating Token Index: 1017

Text #5

Max Range: 0.6123. Min Range: -0.6123

Max Act: 0.5136. Min Act: -0.0001

Data Index: 1449289 (Python Code)

Max Activating Token Index: 956

Text #6

Max Range: 0.6123. Min Range: -0.6123

Max Act: 0.5665. Min Act: -0.0001

Data Index: 1459663 (Python Code)

Max Activating Token Index: 27

Text #7

Max Range: 0.6123. Min Range: -0.6123

Max Act: 0.5589. Min Act: -0.0002

Data Index: 679872 (C4 (Web Text))

Max Activating Token Index: 699

Text #8

Max Range: 0.6123. Min Range: -0.6123

Max Act: 0.5231. Min Act: -0.0001

Data Index: 1623355 (Python Code)

Max Activating Token Index: 1020

Text #9

Max Range: 0.6123. Min Range: -0.6123

Max Act: 0.5508. Min Act: -0.0001

Data Index: 1602695 (Python Code)

Max Activating Token Index: 869

Text #10

Max Range: 0.6123. Min Range: -0.6123

Max Act: 0.5491. Min Act: -0.0001

Data Index: 1599200 (Python Code)

Max Activating Token Index: 1010

Text #11

Max Range: 0.6123. Min Range: -0.6123

Max Act: 0.5170. Min Act: -0.0001

Data Index: 1430707 (Python Code)

Max Activating Token Index: 1016

Text #12

Max Range: 0.6123. Min Range: -0.6123

Max Act: 0.5450. Min Act: -0.0002

Data Index: 970297 (C4 (Web Text))

Max Activating Token Index: 967

Text #13

Max Range: 0.6123. Min Range: -0.6123

Max Act: 0.5392. Min Act: -0.0001

Data Index: 1491794 (Python Code)

Max Activating Token Index: 740

Text #14

Max Range: 0.6123. Min Range: -0.6123

Max Act: 0.5583. Min Act: -0.0002

Data Index: 248543 (C4 (Web Text))

Max Activating Token Index: 68

Text #15

Max Range: 0.6123. Min Range: -0.6123

Max Act: 0.4974. Min Act: -0.0001

Data Index: 1513114 (Python Code)

Max Activating Token Index: 654

Text #16

Max Range: 0.6123. Min Range: -0.6123

Max Act: 0.5392. Min Act: -0.0002

Data Index: 1347258 (C4 (Web Text))

Max Activating Token Index: 909

Text #17

Max Range: 0.6123. Min Range: -0.6123

Max Act: 0.5151. Min Act: -0.0001

Data Index: 1309806 (C4 (Web Text))

Max Activating Token Index: 840

Text #18

Max Range: 0.6123. Min Range: -0.6123

Max Act: 0.5276. Min Act: -0.0001

Data Index: 1489137 (Python Code)

Max Activating Token Index: 1005

Text #19

Max Range: 0.6123. Min Range: -0.6123

Max Act: 0.5155. Min Act: -0.0001

Data Index: 1475961 (Python Code)

Max Activating Token Index: 936