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

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

Neuron 3203 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.1151. Min Act: -0.0001

Data Index: 1453758 (Python Code)

Max Activating Token Index: 641

Text #1

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.1033. Min Act: -0.0001

Data Index: 180834 (C4 (Web Text))

Max Activating Token Index: 621

Text #2

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0999. Min Act: -0.0001

Data Index: 247603 (C4 (Web Text))

Max Activating Token Index: 544

Text #3

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0945. Min Act: -0.0001

Data Index: 152936 (C4 (Web Text))

Max Activating Token Index: 72

Text #4

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0940. Min Act: -0.0001

Data Index: 1647847 (Python Code)

Max Activating Token Index: 54

Text #5

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0901. Min Act: -0.0001

Data Index: 1508133 (Python Code)

Max Activating Token Index: 853

Text #6

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0868. Min Act: -0.0001

Data Index: 1542375 (Python Code)

Max Activating Token Index: 474

Text #7

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0839. Min Act: -0.0001

Data Index: 1654559 (Python Code)

Max Activating Token Index: 679

Text #8

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0856. Min Act: -0.0001

Data Index: 1529798 (Python Code)

Max Activating Token Index: 858

Text #9

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0806. Min Act: -0.0001

Data Index: 1557112 (Python Code)

Max Activating Token Index: 118

Text #10

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0838. Min Act: -0.0001

Data Index: 979045 (C4 (Web Text))

Max Activating Token Index: 249

Text #11

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0797. Min Act: -0.0001

Data Index: 1530353 (Python Code)

Max Activating Token Index: 757

Text #12

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0801. Min Act: -0.0001

Data Index: 551528 (C4 (Web Text))

Max Activating Token Index: 72

Text #13

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0836. Min Act: -0.0001

Data Index: 469552 (C4 (Web Text))

Max Activating Token Index: 590

Text #14

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0799. Min Act: -0.0001

Data Index: 1216165 (C4 (Web Text))

Max Activating Token Index: 219

Text #15

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0841. Min Act: -0.0001

Data Index: 1636388 (Python Code)

Max Activating Token Index: 125

Text #16

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0800. Min Act: -0.0001

Data Index: 1621833 (Python Code)

Max Activating Token Index: 683

Text #17

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0800. Min Act: -0.0001

Data Index: 302828 (C4 (Web Text))

Max Activating Token Index: 935

Text #18

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0783. Min Act: -0.0001

Data Index: 1648475 (Python Code)

Max Activating Token Index: 346

Text #19

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0741. Min Act: -0.0001

Data Index: 1500088 (Python Code)

Max Activating Token Index: 52