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

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

Neuron 5278 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3559. Min Range: -0.3559

Max Act: 0.3559. Min Act: -0.0001

Data Index: 1408440 (Python Code)

Max Activating Token Index: 503

Text #1

Max Range: 0.3559. Min Range: -0.3559

Max Act: 0.3554. Min Act: -0.0001

Data Index: 1534741 (Python Code)

Max Activating Token Index: 551

Text #2

Max Range: 0.3559. Min Range: -0.3559

Max Act: 0.3378. Min Act: -0.0001

Data Index: 1390225 (Python Code)

Max Activating Token Index: 468

Text #3

Max Range: 0.3559. Min Range: -0.3559

Max Act: 0.3168. Min Act: -0.0001

Data Index: 1369617 (Python Code)

Max Activating Token Index: 132

Text #4

Max Range: 0.3559. Min Range: -0.3559

Max Act: 0.3080. Min Act: -0.0001

Data Index: 1506174 (Python Code)

Max Activating Token Index: 185

Text #5

Max Range: 0.3559. Min Range: -0.3559

Max Act: 0.3203. Min Act: -0.0001

Data Index: 1598695 (Python Code)

Max Activating Token Index: 1020

Text #6

Max Range: 0.3559. Min Range: -0.3559

Max Act: 0.2816. Min Act: -0.0001

Data Index: 1458819 (Python Code)

Max Activating Token Index: 298

Text #7

Max Range: 0.3559. Min Range: -0.3559

Max Act: 0.3075. Min Act: -0.0001

Data Index: 1368608 (Python Code)

Max Activating Token Index: 780

Text #8

Max Range: 0.3559. Min Range: -0.3559

Max Act: 0.3082. Min Act: -0.0001

Data Index: 1416167 (Python Code)

Max Activating Token Index: 325

Text #9

Max Range: 0.3559. Min Range: -0.3559

Max Act: 0.2894. Min Act: -0.0001

Data Index: 1527443 (Python Code)

Max Activating Token Index: 72

Text #10

Max Range: 0.3559. Min Range: -0.3559

Max Act: 0.2852. Min Act: -0.0001

Data Index: 1407867 (Python Code)

Max Activating Token Index: 228

Text #11

Max Range: 0.3559. Min Range: -0.3559

Max Act: 0.3122. Min Act: -0.0002

Data Index: 1445546 (Python Code)

Max Activating Token Index: 302

Text #12

Max Range: 0.3559. Min Range: -0.3559

Max Act: 0.2842. Min Act: -0.0001

Data Index: 1429719 (Python Code)

Max Activating Token Index: 169

Text #13

Max Range: 0.3559. Min Range: -0.3559

Max Act: 0.2947. Min Act: -0.0001

Data Index: 1430315 (Python Code)

Max Activating Token Index: 82

Text #14

Max Range: 0.3559. Min Range: -0.3559

Max Act: 0.2781. Min Act: -0.0001

Data Index: 1555436 (Python Code)

Max Activating Token Index: 93

Text #15

Max Range: 0.3559. Min Range: -0.3559

Max Act: 0.2863. Min Act: -0.0001

Data Index: 1587948 (Python Code)

Max Activating Token Index: 47

Text #16

Max Range: 0.3559. Min Range: -0.3559

Max Act: 0.2857. Min Act: -0.0001

Data Index: 1641983 (Python Code)

Max Activating Token Index: 475

Text #17

Max Range: 0.3559. Min Range: -0.3559

Max Act: 0.2795. Min Act: -0.0001

Data Index: 1423192 (Python Code)

Max Activating Token Index: 531

Text #18

Max Range: 0.3559. Min Range: -0.3559

Max Act: 0.2867. Min Act: -0.0001

Data Index: 1559211 (Python Code)

Max Activating Token Index: 591

Text #19

Max Range: 0.3559. Min Range: -0.3559

Max Act: 0.3055. Min Act: -0.0001

Data Index: 1395350 (Python Code)

Max Activating Token Index: 626