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

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

Neuron 3595 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7602. Min Range: -1.7602

Max Act: 1.7602. Min Act: -0.0000

Data Index: 1506206 (Python Code)

Max Activating Token Index: 331

Text #1

Max Range: 1.7602. Min Range: -1.7602

Max Act: 1.6186. Min Act: -0.0000

Data Index: 1499607 (Python Code)

Max Activating Token Index: 732

Text #2

Max Range: 1.7602. Min Range: -1.7602

Max Act: 1.4920. Min Act: -0.0000

Data Index: 1594152 (Python Code)

Max Activating Token Index: 56

Text #3

Max Range: 1.7602. Min Range: -1.7602

Max Act: 1.3982. Min Act: -0.0000

Data Index: 1582402 (Python Code)

Max Activating Token Index: 656

Text #4

Max Range: 1.7602. Min Range: -1.7602

Max Act: 1.3537. Min Act: -0.0000

Data Index: 1429425 (Python Code)

Max Activating Token Index: 86

Text #5

Max Range: 1.7602. Min Range: -1.7602

Max Act: 1.3549. Min Act: -0.0000

Data Index: 1427735 (Python Code)

Max Activating Token Index: 224

Text #6

Max Range: 1.7602. Min Range: -1.7602

Max Act: 1.4029. Min Act: -0.0000

Data Index: 1530821 (Python Code)

Max Activating Token Index: 568

Text #7

Max Range: 1.7602. Min Range: -1.7602

Max Act: 1.2480. Min Act: -0.0000

Data Index: 1603655 (Python Code)

Max Activating Token Index: 931

Text #8

Max Range: 1.7602. Min Range: -1.7602

Max Act: 1.3178. Min Act: -0.0000

Data Index: 1542631 (Python Code)

Max Activating Token Index: 204

Text #9

Max Range: 1.7602. Min Range: -1.7602

Max Act: 1.3121. Min Act: -0.0000

Data Index: 1366067 (Python Code)

Max Activating Token Index: 731

Text #10

Max Range: 1.7602. Min Range: -1.7602

Max Act: 1.3117. Min Act: -0.0000

Data Index: 1533912 (Python Code)

Max Activating Token Index: 75

Text #11

Max Range: 1.7602. Min Range: -1.7602

Max Act: 1.2155. Min Act: -0.0000

Data Index: 1596292 (Python Code)

Max Activating Token Index: 709

Text #12

Max Range: 1.7602. Min Range: -1.7602

Max Act: 1.2890. Min Act: -0.0000

Data Index: 1593488 (Python Code)

Max Activating Token Index: 62

Text #13

Max Range: 1.7602. Min Range: -1.7602

Max Act: 1.2725. Min Act: -0.0000

Data Index: 1509425 (Python Code)

Max Activating Token Index: 73

Text #14

Max Range: 1.7602. Min Range: -1.7602

Max Act: 1.2551. Min Act: -0.0000

Data Index: 1647645 (Python Code)

Max Activating Token Index: 267

Text #15

Max Range: 1.7602. Min Range: -1.7602

Max Act: 1.2034. Min Act: -0.0000

Data Index: 1546797 (Python Code)

Max Activating Token Index: 67

Text #16

Max Range: 1.7602. Min Range: -1.7602

Max Act: 1.2246. Min Act: -0.0000

Data Index: 1431553 (Python Code)

Max Activating Token Index: 253

Text #17

Max Range: 1.7602. Min Range: -1.7602

Max Act: 1.2473. Min Act: -0.0000

Data Index: 1371617 (Python Code)

Max Activating Token Index: 232

Text #18

Max Range: 1.7602. Min Range: -1.7602

Max Act: 1.2372. Min Act: -0.0000

Data Index: 1445560 (Python Code)

Max Activating Token Index: 1012

Text #19

Max Range: 1.7602. Min Range: -1.7602

Max Act: 1.2981. Min Act: -0.0000

Data Index: 1378446 (Python Code)

Max Activating Token Index: 962