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

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

Neuron 6018 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0596. Min Range: -1.0596

Max Act: 1.0596. Min Act: -0.0001

Data Index: 525340 (C4 (Web Text))

Max Activating Token Index: 120

Text #1

Max Range: 1.0596. Min Range: -1.0596

Max Act: 0.9357. Min Act: -0.0001

Data Index: 500463 (C4 (Web Text))

Max Activating Token Index: 21

Text #2

Max Range: 1.0596. Min Range: -1.0596

Max Act: 0.8736. Min Act: -0.0001

Data Index: 929137 (C4 (Web Text))

Max Activating Token Index: 236

Text #3

Max Range: 1.0596. Min Range: -1.0596

Max Act: 0.8908. Min Act: -0.0001

Data Index: 1271138 (C4 (Web Text))

Max Activating Token Index: 792

Text #4

Max Range: 1.0596. Min Range: -1.0596

Max Act: 0.8826. Min Act: -0.0001

Data Index: 65801 (C4 (Web Text))

Max Activating Token Index: 4

Text #5

Max Range: 1.0596. Min Range: -1.0596

Max Act: 0.8824. Min Act: -0.0001

Data Index: 572367 (C4 (Web Text))

Max Activating Token Index: 333

Text #6

Max Range: 1.0596. Min Range: -1.0596

Max Act: 0.8544. Min Act: -0.0001

Data Index: 561684 (C4 (Web Text))

Max Activating Token Index: 30

Text #7

Max Range: 1.0596. Min Range: -1.0596

Max Act: 0.8417. Min Act: -0.0001

Data Index: 732073 (C4 (Web Text))

Max Activating Token Index: 23

Text #8

Max Range: 1.0596. Min Range: -1.0596

Max Act: 0.8569. Min Act: -0.0001

Data Index: 664951 (C4 (Web Text))

Max Activating Token Index: 23

Text #9

Max Range: 1.0596. Min Range: -1.0596

Max Act: 0.8669. Min Act: -0.0001

Data Index: 7699 (C4 (Web Text))

Max Activating Token Index: 533

Text #10

Max Range: 1.0596. Min Range: -1.0596

Max Act: 0.8169. Min Act: -0.0001

Data Index: 524987 (C4 (Web Text))

Max Activating Token Index: 23

Text #11

Max Range: 1.0596. Min Range: -1.0596

Max Act: 0.8111. Min Act: -0.0001

Data Index: 547524 (C4 (Web Text))

Max Activating Token Index: 27

Text #12

Max Range: 1.0596. Min Range: -1.0596

Max Act: 0.8133. Min Act: -0.0001

Data Index: 1162405 (C4 (Web Text))

Max Activating Token Index: 38

Text #13

Max Range: 1.0596. Min Range: -1.0596

Max Act: 0.8037. Min Act: -0.0001

Data Index: 1219482 (C4 (Web Text))

Max Activating Token Index: 312

Text #14

Max Range: 1.0596. Min Range: -1.0596

Max Act: 0.7757. Min Act: -0.0001

Data Index: 1107902 (C4 (Web Text))

Max Activating Token Index: 132

Text #15

Max Range: 1.0596. Min Range: -1.0596

Max Act: 0.7505. Min Act: -0.0001

Data Index: 950880 (C4 (Web Text))

Max Activating Token Index: 887

Text #16

Max Range: 1.0596. Min Range: -1.0596

Max Act: 0.7990. Min Act: -0.0001

Data Index: 544657 (C4 (Web Text))

Max Activating Token Index: 138

Text #17

Max Range: 1.0596. Min Range: -1.0596

Max Act: 0.7709. Min Act: -0.0000

Data Index: 669213 (C4 (Web Text))

Max Activating Token Index: 1019

Text #18

Max Range: 1.0596. Min Range: -1.0596

Max Act: 0.7991. Min Act: -0.0001

Data Index: 278388 (C4 (Web Text))

Max Activating Token Index: 18

Text #19

Max Range: 1.0596. Min Range: -1.0596

Max Act: 0.7700. Min Act: -0.0001

Data Index: 532308 (C4 (Web Text))

Max Activating Token Index: 16