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

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

Neuron 2246 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2865. Min Range: -0.2865

Max Act: 0.2865. Min Act: -0.0000

Data Index: 171766 (C4 (Web Text))

Max Activating Token Index: 790

Text #1

Max Range: 0.2865. Min Range: -0.2865

Max Act: 0.2263. Min Act: -0.0000

Data Index: 707047 (C4 (Web Text))

Max Activating Token Index: 942

Text #2

Max Range: 0.2865. Min Range: -0.2865

Max Act: 0.2168. Min Act: -0.0000

Data Index: 1235848 (C4 (Web Text))

Max Activating Token Index: 887

Text #3

Max Range: 0.2865. Min Range: -0.2865

Max Act: 0.2238. Min Act: -0.0001

Data Index: 661532 (C4 (Web Text))

Max Activating Token Index: 294

Text #4

Max Range: 0.2865. Min Range: -0.2865

Max Act: 0.2052. Min Act: -0.0000

Data Index: 860434 (C4 (Web Text))

Max Activating Token Index: 137

Text #5

Max Range: 0.2865. Min Range: -0.2865

Max Act: 0.2038. Min Act: -0.0000

Data Index: 1281351 (C4 (Web Text))

Max Activating Token Index: 780

Text #6

Max Range: 0.2865. Min Range: -0.2865

Max Act: 0.2098. Min Act: -0.0000

Data Index: 741544 (C4 (Web Text))

Max Activating Token Index: 933

Text #7

Max Range: 0.2865. Min Range: -0.2865

Max Act: 0.2030. Min Act: -0.0000

Data Index: 883027 (C4 (Web Text))

Max Activating Token Index: 681

Text #8

Max Range: 0.2865. Min Range: -0.2865

Max Act: 0.1826. Min Act: -0.0000

Data Index: 520017 (C4 (Web Text))

Max Activating Token Index: 154

Text #9

Max Range: 0.2865. Min Range: -0.2865

Max Act: 0.1697. Min Act: -0.0000

Data Index: 529076 (C4 (Web Text))

Max Activating Token Index: 129

Text #10

Max Range: 0.2865. Min Range: -0.2865

Max Act: 0.1869. Min Act: -0.0000

Data Index: 443775 (C4 (Web Text))

Max Activating Token Index: 125

Text #11

Max Range: 0.2865. Min Range: -0.2865

Max Act: 0.1901. Min Act: -0.0001

Data Index: 737981 (C4 (Web Text))

Max Activating Token Index: 590

Text #12

Max Range: 0.2865. Min Range: -0.2865

Max Act: 0.1758. Min Act: -0.0000

Data Index: 190351 (C4 (Web Text))

Max Activating Token Index: 758

Text #13

Max Range: 0.2865. Min Range: -0.2865

Max Act: 0.1712. Min Act: -0.0000

Data Index: 483426 (C4 (Web Text))

Max Activating Token Index: 731

Text #14

Max Range: 0.2865. Min Range: -0.2865

Max Act: 0.1658. Min Act: -0.0000

Data Index: 51424 (C4 (Web Text))

Max Activating Token Index: 274

Text #15

Max Range: 0.2865. Min Range: -0.2865

Max Act: 0.1573. Min Act: -0.0000

Data Index: 887545 (C4 (Web Text))

Max Activating Token Index: 183

Text #16

Max Range: 0.2865. Min Range: -0.2865

Max Act: 0.1771. Min Act: -0.0000

Data Index: 813580 (C4 (Web Text))

Max Activating Token Index: 1007

Text #17

Max Range: 0.2865. Min Range: -0.2865

Max Act: 0.1698. Min Act: -0.0000

Data Index: 927286 (C4 (Web Text))

Max Activating Token Index: 901

Text #18

Max Range: 0.2865. Min Range: -0.2865

Max Act: 0.1586. Min Act: -0.0000

Data Index: 1217344 (C4 (Web Text))

Max Activating Token Index: 105

Text #19

Max Range: 0.2865. Min Range: -0.2865

Max Act: 0.1744. Min Act: -0.0000

Data Index: 1173973 (C4 (Web Text))

Max Activating Token Index: 726