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

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

Neuron 2755 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: 1.4975. Min Range: -1.4975

Max Act: 1.3705. Min Act: -0.0001

Data Index: 1386604 (Python Code)

Max Activating Token Index: 154

Text #1

Max Range: 1.4975. Min Range: -1.4975

Max Act: 1.4714. Min Act: -0.0001

Data Index: 1491764 (Python Code)

Max Activating Token Index: 70

Text #2

Max Range: 1.4975. Min Range: -1.4975

Max Act: 1.4975. Min Act: -0.0001

Data Index: 1497541 (Python Code)

Max Activating Token Index: 588

Text #3

Max Range: 1.4975. Min Range: -1.4975

Max Act: 1.4769. Min Act: -0.0001

Data Index: 1382760 (Python Code)

Max Activating Token Index: 191

Text #4

Max Range: 1.4975. Min Range: -1.4975

Max Act: 1.4109. Min Act: -0.0001

Data Index: 1426109 (Python Code)

Max Activating Token Index: 594

Text #5

Max Range: 1.4975. Min Range: -1.4975

Max Act: 1.3815. Min Act: -0.0001

Data Index: 1613098 (Python Code)

Max Activating Token Index: 64

Text #6

Max Range: 1.4975. Min Range: -1.4975

Max Act: 1.3731. Min Act: -0.0001

Data Index: 1561785 (Python Code)

Max Activating Token Index: 7

Text #7

Max Range: 1.4975. Min Range: -1.4975

Max Act: 1.3260. Min Act: -0.0001

Data Index: 1438934 (Python Code)

Max Activating Token Index: 602

Text #8

Max Range: 1.4975. Min Range: -1.4975

Max Act: 1.3112. Min Act: -0.0001

Data Index: 1452864 (Python Code)

Max Activating Token Index: 192

Text #9

Max Range: 1.4975. Min Range: -1.4975

Max Act: 1.3361. Min Act: -0.0001

Data Index: 1505935 (Python Code)

Max Activating Token Index: 413

Text #10

Max Range: 1.4975. Min Range: -1.4975

Max Act: 1.3021. Min Act: -0.0001

Data Index: 1590526 (Python Code)

Max Activating Token Index: 108

Text #11

Max Range: 1.4975. Min Range: -1.4975

Max Act: 1.3336. Min Act: -0.0001

Data Index: 1432800 (Python Code)

Max Activating Token Index: 467

Text #12

Max Range: 1.4975. Min Range: -1.4975

Max Act: 1.2330. Min Act: -0.0001

Data Index: 1477764 (Python Code)

Max Activating Token Index: 168

Text #13

Max Range: 1.4975. Min Range: -1.4975

Max Act: 1.2727. Min Act: -0.0001

Data Index: 1601286 (Python Code)

Max Activating Token Index: 125

Text #14

Max Range: 1.4975. Min Range: -1.4975

Max Act: 1.2344. Min Act: -0.0001

Data Index: 1431177 (Python Code)

Max Activating Token Index: 293

Text #15

Max Range: 1.4975. Min Range: -1.4975

Max Act: 1.2977. Min Act: -0.0001

Data Index: 1630004 (Python Code)

Max Activating Token Index: 469

Text #16

Max Range: 1.4975. Min Range: -1.4975

Max Act: 1.3236. Min Act: -0.0001

Data Index: 1571641 (Python Code)

Max Activating Token Index: 893

Text #17

Max Range: 1.4975. Min Range: -1.4975

Max Act: 1.2926. Min Act: -0.0001

Data Index: 1484686 (Python Code)

Max Activating Token Index: 172

Text #18

Max Range: 1.4975. Min Range: -1.4975

Max Act: 1.2059. Min Act: -0.0001

Data Index: 1569920 (Python Code)

Max Activating Token Index: 855

Text #19

Max Range: 1.4975. Min Range: -1.4975

Max Act: 1.1691. Min Act: -0.0001

Data Index: 1407882 (Python Code)

Max Activating Token Index: 403