Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1782 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.3141. Min Act: -0.0001

Data Index: 1037378 (C4 (Web Text))

Max Activating Token Index: 962

Text #1

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.3303. Min Act: -0.0001

Data Index: 94103 (C4 (Web Text))

Max Activating Token Index: 878

Text #2

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.3015. Min Act: -0.0001

Data Index: 705703 (C4 (Web Text))

Max Activating Token Index: 532

Text #3

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.3175. Min Act: -0.0001

Data Index: 99140 (C4 (Web Text))

Max Activating Token Index: 488

Text #4

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2964. Min Act: -0.0001

Data Index: 841103 (C4 (Web Text))

Max Activating Token Index: 37

Text #5

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2917. Min Act: -0.0001

Data Index: 319445 (C4 (Web Text))

Max Activating Token Index: 156

Text #6

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2721. Min Act: -0.0001

Data Index: 685005 (C4 (Web Text))

Max Activating Token Index: 80

Text #7

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2925. Min Act: -0.0001

Data Index: 122594 (C4 (Web Text))

Max Activating Token Index: 224

Text #8

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2976. Min Act: -0.0001

Data Index: 774151 (C4 (Web Text))

Max Activating Token Index: 618

Text #9

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2873. Min Act: -0.0001

Data Index: 596720 (C4 (Web Text))

Max Activating Token Index: 697

Text #10

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2836. Min Act: -0.0001

Data Index: 980604 (C4 (Web Text))

Max Activating Token Index: 720

Text #11

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2678. Min Act: -0.0001

Data Index: 549700 (C4 (Web Text))

Max Activating Token Index: 438

Text #12

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2838. Min Act: -0.0001

Data Index: 464494 (C4 (Web Text))

Max Activating Token Index: 67

Text #13

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2707. Min Act: -0.0001

Data Index: 956064 (C4 (Web Text))

Max Activating Token Index: 823

Text #14

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2640. Min Act: -0.0001

Data Index: 1128483 (C4 (Web Text))

Max Activating Token Index: 207

Text #15

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2676. Min Act: -0.0001

Data Index: 1250739 (C4 (Web Text))

Max Activating Token Index: 363

Text #16

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2340. Min Act: -0.0001

Data Index: 962940 (C4 (Web Text))

Max Activating Token Index: 643

Text #17

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2391. Min Act: -0.0001

Data Index: 713951 (C4 (Web Text))

Max Activating Token Index: 757

Text #18

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2417. Min Act: -0.0001

Data Index: 806665 (C4 (Web Text))

Max Activating Token Index: 408

Text #19

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2260. Min Act: -0.0001

Data Index: 474733 (C4 (Web Text))

Max Activating Token Index: 852