Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1090 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.8755. Min Range: -3.8755

Max Act: 3.8755. Min Act: -0.0000

Data Index: 277863 (C4 (Web Text))

Max Activating Token Index: 113

Text #1

Max Range: 3.8755. Min Range: -3.8755

Max Act: 3.4285. Min Act: -0.0000

Data Index: 103079 (C4 (Web Text))

Max Activating Token Index: 420

Text #2

Max Range: 3.8755. Min Range: -3.8755

Max Act: 3.3705. Min Act: -0.0000

Data Index: 1521768 (Python Code)

Max Activating Token Index: 527

Text #3

Max Range: 3.8755. Min Range: -3.8755

Max Act: 3.2680. Min Act: -0.0000

Data Index: 1655815 (Python Code)

Max Activating Token Index: 165

Text #4

Max Range: 3.8755. Min Range: -3.8755

Max Act: 3.4010. Min Act: -0.0001

Data Index: 206100 (C4 (Web Text))

Max Activating Token Index: 433

Text #5

Max Range: 3.8755. Min Range: -3.8755

Max Act: 2.8581. Min Act: -0.0001

Data Index: 440382 (C4 (Web Text))

Max Activating Token Index: 1022

Text #6

Max Range: 3.8755. Min Range: -3.8755

Max Act: 2.8152. Min Act: -0.0001

Data Index: 419600 (C4 (Web Text))

Max Activating Token Index: 589

Text #7

Max Range: 3.8755. Min Range: -3.8755

Max Act: 2.5069. Min Act: -0.0000

Data Index: 938299 (C4 (Web Text))

Max Activating Token Index: 360

Text #8

Max Range: 3.8755. Min Range: -3.8755

Max Act: 2.6231. Min Act: -0.0000

Data Index: 754254 (C4 (Web Text))

Max Activating Token Index: 85

Text #9

Max Range: 3.8755. Min Range: -3.8755

Max Act: 2.7299. Min Act: -0.0000

Data Index: 119924 (C4 (Web Text))

Max Activating Token Index: 99

Text #10

Max Range: 3.8755. Min Range: -3.8755

Max Act: 2.8389. Min Act: -0.0000

Data Index: 1533103 (Python Code)

Max Activating Token Index: 839

Text #11

Max Range: 3.8755. Min Range: -3.8755

Max Act: 2.6653. Min Act: -0.0000

Data Index: 1234782 (C4 (Web Text))

Max Activating Token Index: 601

Text #12

Max Range: 3.8755. Min Range: -3.8755

Max Act: 2.6219. Min Act: -0.0000

Data Index: 194455 (C4 (Web Text))

Max Activating Token Index: 386

Text #13

Max Range: 3.8755. Min Range: -3.8755

Max Act: 2.4664. Min Act: -0.0000

Data Index: 1260902 (C4 (Web Text))

Max Activating Token Index: 181

Text #14

Max Range: 3.8755. Min Range: -3.8755

Max Act: 2.2073. Min Act: -0.0000

Data Index: 1213705 (C4 (Web Text))

Max Activating Token Index: 152

Text #15

Max Range: 3.8755. Min Range: -3.8755

Max Act: 2.5624. Min Act: -0.0000

Data Index: 778450 (C4 (Web Text))

Max Activating Token Index: 615

Text #16

Max Range: 3.8755. Min Range: -3.8755

Max Act: 2.5489. Min Act: -0.0001

Data Index: 941011 (C4 (Web Text))

Max Activating Token Index: 191

Text #17

Max Range: 3.8755. Min Range: -3.8755

Max Act: 2.5227. Min Act: -0.0000

Data Index: 206002 (C4 (Web Text))

Max Activating Token Index: 26

Text #18

Max Range: 3.8755. Min Range: -3.8755

Max Act: 2.8577. Min Act: -0.0000

Data Index: 521005 (C4 (Web Text))

Max Activating Token Index: 158

Text #19

Max Range: 3.8755. Min Range: -3.8755

Max Act: 2.4257. Min Act: -0.0000

Data Index: 654483 (C4 (Web Text))

Max Activating Token Index: 740