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

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

Neuron 4160 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6140. Min Range: -1.6140

Max Act: 1.6140. Min Act: -0.0000

Data Index: 207568 (C4 (Web Text))

Max Activating Token Index: 377

Text #1

Max Range: 1.6140. Min Range: -1.6140

Max Act: 1.3182. Min Act: -0.0000

Data Index: 1195766 (C4 (Web Text))

Max Activating Token Index: 17

Text #2

Max Range: 1.6140. Min Range: -1.6140

Max Act: 1.1433. Min Act: -0.0000

Data Index: 506070 (C4 (Web Text))

Max Activating Token Index: 214

Text #3

Max Range: 1.6140. Min Range: -1.6140

Max Act: 1.2344. Min Act: -0.0000

Data Index: 884837 (C4 (Web Text))

Max Activating Token Index: 716

Text #4

Max Range: 1.6140. Min Range: -1.6140

Max Act: 1.2360. Min Act: -0.0000

Data Index: 381298 (C4 (Web Text))

Max Activating Token Index: 677

Text #5

Max Range: 1.6140. Min Range: -1.6140

Max Act: 1.2193. Min Act: -0.0000

Data Index: 982221 (C4 (Web Text))

Max Activating Token Index: 435

Text #6

Max Range: 1.6140. Min Range: -1.6140

Max Act: 1.1820. Min Act: -0.0000

Data Index: 1026654 (C4 (Web Text))

Max Activating Token Index: 271

Text #7

Max Range: 1.6140. Min Range: -1.6140

Max Act: 1.1021. Min Act: -0.0000

Data Index: 478128 (C4 (Web Text))

Max Activating Token Index: 39

Text #8

Max Range: 1.6140. Min Range: -1.6140

Max Act: 1.0987. Min Act: -0.0000

Data Index: 543902 (C4 (Web Text))

Max Activating Token Index: 145

Text #9

Max Range: 1.6140. Min Range: -1.6140

Max Act: 1.1117. Min Act: -0.0000

Data Index: 1296229 (C4 (Web Text))

Max Activating Token Index: 560

Text #10

Max Range: 1.6140. Min Range: -1.6140

Max Act: 1.1741. Min Act: -0.0001

Data Index: 869576 (C4 (Web Text))

Max Activating Token Index: 121

Text #11

Max Range: 1.6140. Min Range: -1.6140

Max Act: 1.2062. Min Act: -0.0000

Data Index: 928977 (C4 (Web Text))

Max Activating Token Index: 790

Text #12

Max Range: 1.6140. Min Range: -1.6140

Max Act: 1.1342. Min Act: -0.0000

Data Index: 409394 (C4 (Web Text))

Max Activating Token Index: 234

Text #13

Max Range: 1.6140. Min Range: -1.6140

Max Act: 1.0507. Min Act: -0.0000

Data Index: 756173 (C4 (Web Text))

Max Activating Token Index: 1008

Text #14

Max Range: 1.6140. Min Range: -1.6140

Max Act: 1.1582. Min Act: -0.0000

Data Index: 500731 (C4 (Web Text))

Max Activating Token Index: 768

Text #15

Max Range: 1.6140. Min Range: -1.6140

Max Act: 1.0561. Min Act: -0.0000

Data Index: 795750 (C4 (Web Text))

Max Activating Token Index: 699

Text #16

Max Range: 1.6140. Min Range: -1.6140

Max Act: 1.1077. Min Act: -0.0000

Data Index: 821310 (C4 (Web Text))

Max Activating Token Index: 76

Text #17

Max Range: 1.6140. Min Range: -1.6140

Max Act: 1.0432. Min Act: -0.0000

Data Index: 1183261 (C4 (Web Text))

Max Activating Token Index: 450

Text #18

Max Range: 1.6140. Min Range: -1.6140

Max Act: 1.0563. Min Act: -0.0000

Data Index: 294718 (C4 (Web Text))

Max Activating Token Index: 170

Text #19

Max Range: 1.6140. Min Range: -1.6140

Max Act: 1.0441. Min Act: -0.0000

Data Index: 1244112 (C4 (Web Text))

Max Activating Token Index: 156