Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2308 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.0105. Min Range: -3.0105

Max Act: 3.0105. Min Act: -0.0000

Data Index: 1425735 (Python Code)

Max Activating Token Index: 882

Text #1

Max Range: 3.0105. Min Range: -3.0105

Max Act: 2.5759. Min Act: -0.0000

Data Index: 1033866 (C4 (Web Text))

Max Activating Token Index: 883

Text #2

Max Range: 3.0105. Min Range: -3.0105

Max Act: 2.5074. Min Act: -0.0000

Data Index: 1498769 (Python Code)

Max Activating Token Index: 1020

Text #3

Max Range: 3.0105. Min Range: -3.0105

Max Act: 2.4405. Min Act: -0.0000

Data Index: 1552621 (Python Code)

Max Activating Token Index: 827

Text #4

Max Range: 3.0105. Min Range: -3.0105

Max Act: 2.6385. Min Act: -0.0000

Data Index: 1624052 (Python Code)

Max Activating Token Index: 973

Text #5

Max Range: 3.0105. Min Range: -3.0105

Max Act: 2.5967. Min Act: -0.0000

Data Index: 1490790 (Python Code)

Max Activating Token Index: 832

Text #6

Max Range: 3.0105. Min Range: -3.0105

Max Act: 2.5701. Min Act: -0.0000

Data Index: 1532122 (Python Code)

Max Activating Token Index: 1015

Text #7

Max Range: 3.0105. Min Range: -3.0105

Max Act: 2.3958. Min Act: -0.0000

Data Index: 1526707 (Python Code)

Max Activating Token Index: 987

Text #8

Max Range: 3.0105. Min Range: -3.0105

Max Act: 2.3873. Min Act: -0.0000

Data Index: 1161682 (C4 (Web Text))

Max Activating Token Index: 915

Text #9

Max Range: 3.0105. Min Range: -3.0105

Max Act: 2.3645. Min Act: -0.0000

Data Index: 1548642 (Python Code)

Max Activating Token Index: 811

Text #10

Max Range: 3.0105. Min Range: -3.0105

Max Act: 2.7666. Min Act: -0.0000

Data Index: 1198539 (C4 (Web Text))

Max Activating Token Index: 966

Text #11

Max Range: 3.0105. Min Range: -3.0105

Max Act: 2.1333. Min Act: -0.0000

Data Index: 783567 (C4 (Web Text))

Max Activating Token Index: 341

Text #12

Max Range: 3.0105. Min Range: -3.0105

Max Act: 2.4731. Min Act: -0.0000

Data Index: 1431641 (Python Code)

Max Activating Token Index: 1017

Text #13

Max Range: 3.0105. Min Range: -3.0105

Max Act: 2.3309. Min Act: -0.0000

Data Index: 452007 (C4 (Web Text))

Max Activating Token Index: 108

Text #14

Max Range: 3.0105. Min Range: -3.0105

Max Act: 2.2797. Min Act: -0.0000

Data Index: 1482813 (Python Code)

Max Activating Token Index: 912

Text #15

Max Range: 3.0105. Min Range: -3.0105

Max Act: 2.3723. Min Act: -0.0000

Data Index: 1651680 (Python Code)

Max Activating Token Index: 891

Text #16

Max Range: 3.0105. Min Range: -3.0105

Max Act: 2.3668. Min Act: -0.0000

Data Index: 1508341 (Python Code)

Max Activating Token Index: 894

Text #17

Max Range: 3.0105. Min Range: -3.0105

Max Act: 2.3659. Min Act: -0.0000

Data Index: 1574688 (Python Code)

Max Activating Token Index: 1019

Text #18

Max Range: 3.0105. Min Range: -3.0105

Max Act: 2.3711. Min Act: -0.0000

Data Index: 1430042 (Python Code)

Max Activating Token Index: 1006

Text #19

Max Range: 3.0105. Min Range: -3.0105

Max Act: 2.3510. Min Act: -0.0000

Data Index: 1384274 (Python Code)

Max Activating Token Index: 389