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

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

Neuron 1850 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4142. Min Range: -3.4142

Max Act: 3.3393. Min Act: -0.0000

Data Index: 530751 (C4 (Web Text))

Max Activating Token Index: 909

Text #1

Max Range: 3.4142. Min Range: -3.4142

Max Act: 3.4142. Min Act: -0.0000

Data Index: 1216391 (C4 (Web Text))

Max Activating Token Index: 89

Text #2

Max Range: 3.4142. Min Range: -3.4142

Max Act: 3.1159. Min Act: -0.0000

Data Index: 582985 (C4 (Web Text))

Max Activating Token Index: 470

Text #3

Max Range: 3.4142. Min Range: -3.4142

Max Act: 3.0252. Min Act: -0.0000

Data Index: 337212 (C4 (Web Text))

Max Activating Token Index: 794

Text #4

Max Range: 3.4142. Min Range: -3.4142

Max Act: 3.1433. Min Act: -0.0000

Data Index: 844225 (C4 (Web Text))

Max Activating Token Index: 820

Text #5

Max Range: 3.4142. Min Range: -3.4142

Max Act: 2.9391. Min Act: -0.0000

Data Index: 50714 (C4 (Web Text))

Max Activating Token Index: 333

Text #6

Max Range: 3.4142. Min Range: -3.4142

Max Act: 2.5658. Min Act: -0.0000

Data Index: 1038626 (C4 (Web Text))

Max Activating Token Index: 155

Text #7

Max Range: 3.4142. Min Range: -3.4142

Max Act: 2.7318. Min Act: -0.0000

Data Index: 1090151 (C4 (Web Text))

Max Activating Token Index: 665

Text #8

Max Range: 3.4142. Min Range: -3.4142

Max Act: 2.9591. Min Act: -0.0000

Data Index: 1236248 (C4 (Web Text))

Max Activating Token Index: 310

Text #9

Max Range: 3.4142. Min Range: -3.4142

Max Act: 2.5567. Min Act: -0.0000

Data Index: 895410 (C4 (Web Text))

Max Activating Token Index: 266

Text #10

Max Range: 3.4142. Min Range: -3.4142

Max Act: 2.5583. Min Act: -0.0000

Data Index: 137951 (C4 (Web Text))

Max Activating Token Index: 72

Text #11

Max Range: 3.4142. Min Range: -3.4142

Max Act: 2.4288. Min Act: -0.0000

Data Index: 635793 (C4 (Web Text))

Max Activating Token Index: 976

Text #12

Max Range: 3.4142. Min Range: -3.4142

Max Act: 2.3903. Min Act: -0.0000

Data Index: 142378 (C4 (Web Text))

Max Activating Token Index: 243

Text #13

Max Range: 3.4142. Min Range: -3.4142

Max Act: 2.3622. Min Act: -0.0000

Data Index: 159207 (C4 (Web Text))

Max Activating Token Index: 286

Text #14

Max Range: 3.4142. Min Range: -3.4142

Max Act: 2.3389. Min Act: -0.0000

Data Index: 1156522 (C4 (Web Text))

Max Activating Token Index: 703

Text #15

Max Range: 3.4142. Min Range: -3.4142

Max Act: 2.1651. Min Act: -0.0000

Data Index: 1265030 (C4 (Web Text))

Max Activating Token Index: 65

Text #16

Max Range: 3.4142. Min Range: -3.4142

Max Act: 2.2750. Min Act: -0.0000

Data Index: 1253483 (C4 (Web Text))

Max Activating Token Index: 561

Text #17

Max Range: 3.4142. Min Range: -3.4142

Max Act: 2.0991. Min Act: -0.0000

Data Index: 837961 (C4 (Web Text))

Max Activating Token Index: 596

Text #18

Max Range: 3.4142. Min Range: -3.4142

Max Act: 2.3155. Min Act: -0.0000

Data Index: 904793 (C4 (Web Text))

Max Activating Token Index: 886

Text #19

Max Range: 3.4142. Min Range: -3.4142

Max Act: 2.0553. Min Act: -0.0000

Data Index: 1231036 (C4 (Web Text))

Max Activating Token Index: 413