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

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

Neuron 4052 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2420. Min Range: -0.2420

Max Act: 0.2218. Min Act: -0.0001

Data Index: 1651943 (Python Code)

Max Activating Token Index: 204

Text #1

Max Range: 0.2420. Min Range: -0.2420

Max Act: 0.2420. Min Act: -0.0001

Data Index: 1482099 (Python Code)

Max Activating Token Index: 992

Text #2

Max Range: 0.2420. Min Range: -0.2420

Max Act: 0.2154. Min Act: -0.0001

Data Index: 1350823 (C4 (Web Text))

Max Activating Token Index: 143

Text #3

Max Range: 0.2420. Min Range: -0.2420

Max Act: 0.2015. Min Act: -0.0001

Data Index: 1534784 (Python Code)

Max Activating Token Index: 904

Text #4

Max Range: 0.2420. Min Range: -0.2420

Max Act: 0.2012. Min Act: -0.0001

Data Index: 579458 (C4 (Web Text))

Max Activating Token Index: 495

Text #5

Max Range: 0.2420. Min Range: -0.2420

Max Act: 0.2033. Min Act: -0.0000

Data Index: 274802 (C4 (Web Text))

Max Activating Token Index: 148

Text #6

Max Range: 0.2420. Min Range: -0.2420

Max Act: 0.2047. Min Act: -0.0001

Data Index: 1436018 (Python Code)

Max Activating Token Index: 769

Text #7

Max Range: 0.2420. Min Range: -0.2420

Max Act: 0.2061. Min Act: -0.0001

Data Index: 813168 (C4 (Web Text))

Max Activating Token Index: 949

Text #8

Max Range: 0.2420. Min Range: -0.2420

Max Act: 0.1921. Min Act: -0.0001

Data Index: 1563261 (Python Code)

Max Activating Token Index: 858

Text #9

Max Range: 0.2420. Min Range: -0.2420

Max Act: 0.1920. Min Act: -0.0001

Data Index: 1654752 (Python Code)

Max Activating Token Index: 74

Text #10

Max Range: 0.2420. Min Range: -0.2420

Max Act: 0.1920. Min Act: -0.0001

Data Index: 1571980 (Python Code)

Max Activating Token Index: 312

Text #11

Max Range: 0.2420. Min Range: -0.2420

Max Act: 0.2206. Min Act: -0.0001

Data Index: 886442 (C4 (Web Text))

Max Activating Token Index: 909

Text #12

Max Range: 0.2420. Min Range: -0.2420

Max Act: 0.1979. Min Act: -0.0001

Data Index: 117616 (C4 (Web Text))

Max Activating Token Index: 116

Text #13

Max Range: 0.2420. Min Range: -0.2420

Max Act: 0.1788. Min Act: -0.0001

Data Index: 1428379 (Python Code)

Max Activating Token Index: 756

Text #14

Max Range: 0.2420. Min Range: -0.2420

Max Act: 0.1834. Min Act: -0.0001

Data Index: 1580174 (Python Code)

Max Activating Token Index: 88

Text #15

Max Range: 0.2420. Min Range: -0.2420

Max Act: 0.1813. Min Act: -0.0001

Data Index: 1293228 (C4 (Web Text))

Max Activating Token Index: 713

Text #16

Max Range: 0.2420. Min Range: -0.2420

Max Act: 0.1804. Min Act: -0.0001

Data Index: 1446349 (Python Code)

Max Activating Token Index: 313

Text #17

Max Range: 0.2420. Min Range: -0.2420

Max Act: 0.1782. Min Act: -0.0001

Data Index: 1641340 (Python Code)

Max Activating Token Index: 923

Text #18

Max Range: 0.2420. Min Range: -0.2420

Max Act: 0.1724. Min Act: -0.0001

Data Index: 1505874 (Python Code)

Max Activating Token Index: 755

Text #19

Max Range: 0.2420. Min Range: -0.2420

Max Act: 0.1780. Min Act: -0.0001

Data Index: 1501636 (Python Code)

Max Activating Token Index: 696