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

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

Neuron 650 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.1154. Min Act: -0.0001

Data Index: 1127864 (C4 (Web Text))

Max Activating Token Index: 486

Text #1

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.1077. Min Act: -0.0001

Data Index: 1436166 (Python Code)

Max Activating Token Index: 18

Text #2

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.1016. Min Act: -0.0001

Data Index: 1415710 (Python Code)

Max Activating Token Index: 179

Text #3

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0963. Min Act: -0.0001

Data Index: 1476149 (Python Code)

Max Activating Token Index: 190

Text #4

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0812. Min Act: -0.0001

Data Index: 1619015 (Python Code)

Max Activating Token Index: 1006

Text #5

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0894. Min Act: -0.0001

Data Index: 1128316 (C4 (Web Text))

Max Activating Token Index: 587

Text #6

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0783. Min Act: -0.0001

Data Index: 1021114 (C4 (Web Text))

Max Activating Token Index: 888

Text #7

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0855. Min Act: -0.0001

Data Index: 1446395 (Python Code)

Max Activating Token Index: 163

Text #8

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0852. Min Act: -0.0001

Data Index: 1084091 (C4 (Web Text))

Max Activating Token Index: 318

Text #9

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0842. Min Act: -0.0001

Data Index: 1510318 (Python Code)

Max Activating Token Index: 22

Text #10

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0838. Min Act: -0.0001

Data Index: 1603723 (Python Code)

Max Activating Token Index: 366

Text #11

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0836. Min Act: -0.0001

Data Index: 1098110 (C4 (Web Text))

Max Activating Token Index: 1020

Text #12

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0868. Min Act: -0.0001

Data Index: 191562 (C4 (Web Text))

Max Activating Token Index: 963

Text #13

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0881. Min Act: -0.0001

Data Index: 1280252 (C4 (Web Text))

Max Activating Token Index: 973

Text #14

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0794. Min Act: -0.0001

Data Index: 179560 (C4 (Web Text))

Max Activating Token Index: 123

Text #15

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0810. Min Act: -0.0001

Data Index: 1349047 (C4 (Web Text))

Max Activating Token Index: 780

Text #16

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0758. Min Act: -0.0001

Data Index: 674983 (C4 (Web Text))

Max Activating Token Index: 834

Text #17

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0845. Min Act: -0.0001

Data Index: 1160126 (C4 (Web Text))

Max Activating Token Index: 1004

Text #18

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0872. Min Act: -0.0001

Data Index: 1312200 (C4 (Web Text))

Max Activating Token Index: 802

Text #19

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0749. Min Act: -0.0001

Data Index: 805299 (C4 (Web Text))

Max Activating Token Index: 477