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

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

Neuron 3892 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9217. Min Range: -1.9217

Max Act: 1.8105. Min Act: -0.0000

Data Index: 1625856 (Python Code)

Max Activating Token Index: 267

Text #1

Max Range: 1.9217. Min Range: -1.9217

Max Act: 1.9217. Min Act: -0.0000

Data Index: 1614141 (Python Code)

Max Activating Token Index: 138

Text #2

Max Range: 1.9217. Min Range: -1.9217

Max Act: 1.7679. Min Act: -0.0000

Data Index: 1454029 (Python Code)

Max Activating Token Index: 565

Text #3

Max Range: 1.9217. Min Range: -1.9217

Max Act: 1.6415. Min Act: -0.0001

Data Index: 1498477 (Python Code)

Max Activating Token Index: 712

Text #4

Max Range: 1.9217. Min Range: -1.9217

Max Act: 1.5269. Min Act: -0.0000

Data Index: 1600769 (Python Code)

Max Activating Token Index: 393

Text #5

Max Range: 1.9217. Min Range: -1.9217

Max Act: 1.5473. Min Act: -0.0001

Data Index: 1470336 (Python Code)

Max Activating Token Index: 63

Text #6

Max Range: 1.9217. Min Range: -1.9217

Max Act: 1.5630. Min Act: -0.0000

Data Index: 1442358 (Python Code)

Max Activating Token Index: 701

Text #7

Max Range: 1.9217. Min Range: -1.9217

Max Act: 1.4597. Min Act: -0.0001

Data Index: 1367379 (Python Code)

Max Activating Token Index: 573

Text #8

Max Range: 1.9217. Min Range: -1.9217

Max Act: 1.4937. Min Act: -0.0001

Data Index: 1549556 (Python Code)

Max Activating Token Index: 417

Text #9

Max Range: 1.9217. Min Range: -1.9217

Max Act: 1.4552. Min Act: -0.0000

Data Index: 1590133 (Python Code)

Max Activating Token Index: 851

Text #10

Max Range: 1.9217. Min Range: -1.9217

Max Act: 1.4181. Min Act: -0.0001

Data Index: 1505025 (Python Code)

Max Activating Token Index: 181

Text #11

Max Range: 1.9217. Min Range: -1.9217

Max Act: 1.4180. Min Act: -0.0001

Data Index: 1585622 (Python Code)

Max Activating Token Index: 123

Text #12

Max Range: 1.9217. Min Range: -1.9217

Max Act: 1.5230. Min Act: -0.0001

Data Index: 1379704 (Python Code)

Max Activating Token Index: 627

Text #13

Max Range: 1.9217. Min Range: -1.9217

Max Act: 1.4939. Min Act: -0.0001

Data Index: 1568845 (Python Code)

Max Activating Token Index: 145

Text #14

Max Range: 1.9217. Min Range: -1.9217

Max Act: 1.5158. Min Act: -0.0000

Data Index: 1364665 (Python Code)

Max Activating Token Index: 299

Text #15

Max Range: 1.9217. Min Range: -1.9217

Max Act: 1.3962. Min Act: -0.0000

Data Index: 1394150 (Python Code)

Max Activating Token Index: 114

Text #16

Max Range: 1.9217. Min Range: -1.9217

Max Act: 1.4865. Min Act: -0.0001

Data Index: 1545899 (Python Code)

Max Activating Token Index: 811

Text #17

Max Range: 1.9217. Min Range: -1.9217

Max Act: 1.3596. Min Act: -0.0001

Data Index: 1532058 (Python Code)

Max Activating Token Index: 502

Text #18

Max Range: 1.9217. Min Range: -1.9217

Max Act: 1.5110. Min Act: -0.0000

Data Index: 1512050 (Python Code)

Max Activating Token Index: 796

Text #19

Max Range: 1.9217. Min Range: -1.9217

Max Act: 1.3311. Min Act: -0.0001

Data Index: 1487976 (Python Code)

Max Activating Token Index: 887