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

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

Neuron 3971 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3952. Min Range: -0.3952

Max Act: 0.3952. Min Act: -0.0003

Data Index: 1559819 (Python Code)

Max Activating Token Index: 7

Text #1

Max Range: 0.3952. Min Range: -0.3952

Max Act: 0.3215. Min Act: -0.0003

Data Index: 967857 (C4 (Web Text))

Max Activating Token Index: 22

Text #2

Max Range: 0.3952. Min Range: -0.3952

Max Act: 0.3059. Min Act: -0.0003

Data Index: 1655993 (Python Code)

Max Activating Token Index: 272

Text #3

Max Range: 0.3952. Min Range: -0.3952

Max Act: 0.2991. Min Act: -0.0003

Data Index: 1642308 (Python Code)

Max Activating Token Index: 14

Text #4

Max Range: 0.3952. Min Range: -0.3952

Max Act: 0.3105. Min Act: -0.0003

Data Index: 1438922 (Python Code)

Max Activating Token Index: 203

Text #5

Max Range: 0.3952. Min Range: -0.3952

Max Act: 0.2970. Min Act: -0.0003

Data Index: 1522056 (Python Code)

Max Activating Token Index: 605

Text #6

Max Range: 0.3952. Min Range: -0.3952

Max Act: 0.2952. Min Act: -0.0003

Data Index: 802536 (C4 (Web Text))

Max Activating Token Index: 250

Text #7

Max Range: 0.3952. Min Range: -0.3952

Max Act: 0.2839. Min Act: -0.0003

Data Index: 1367414 (Python Code)

Max Activating Token Index: 16

Text #8

Max Range: 0.3952. Min Range: -0.3952

Max Act: 0.2823. Min Act: -0.0003

Data Index: 1592564 (Python Code)

Max Activating Token Index: 901

Text #9

Max Range: 0.3952. Min Range: -0.3952

Max Act: 0.2722. Min Act: -0.0003

Data Index: 1653577 (Python Code)

Max Activating Token Index: 65

Text #10

Max Range: 0.3952. Min Range: -0.3952

Max Act: 0.2724. Min Act: -0.0003

Data Index: 1439431 (Python Code)

Max Activating Token Index: 60

Text #11

Max Range: 0.3952. Min Range: -0.3952

Max Act: 0.2715. Min Act: -0.0003

Data Index: 1457598 (Python Code)

Max Activating Token Index: 7

Text #12

Max Range: 0.3952. Min Range: -0.3952

Max Act: 0.2712. Min Act: -0.0003

Data Index: 1555696 (Python Code)

Max Activating Token Index: 6

Text #13

Max Range: 0.3952. Min Range: -0.3952

Max Act: 0.2789. Min Act: -0.0003

Data Index: 1574669 (Python Code)

Max Activating Token Index: 20

Text #14

Max Range: 0.3952. Min Range: -0.3952

Max Act: 0.2761. Min Act: -0.0002

Data Index: 1606965 (Python Code)

Max Activating Token Index: 232

Text #15

Max Range: 0.3952. Min Range: -0.3952

Max Act: 0.2766. Min Act: -0.0003

Data Index: 1520654 (Python Code)

Max Activating Token Index: 121

Text #16

Max Range: 0.3952. Min Range: -0.3952

Max Act: 0.2752. Min Act: -0.0003

Data Index: 1614000 (Python Code)

Max Activating Token Index: 137

Text #17

Max Range: 0.3952. Min Range: -0.3952

Max Act: 0.2612. Min Act: -0.0003

Data Index: 1612464 (Python Code)

Max Activating Token Index: 187

Text #18

Max Range: 0.3952. Min Range: -0.3952

Max Act: 0.2719. Min Act: -0.0003

Data Index: 727216 (C4 (Web Text))

Max Activating Token Index: 539

Text #19

Max Range: 0.3952. Min Range: -0.3952

Max Act: 0.2681. Min Act: -0.0003

Data Index: 1567041 (Python Code)

Max Activating Token Index: 124