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

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

Neuron 2873 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8185. Min Range: -1.8185

Max Act: 1.8185. Min Act: -0.0000

Data Index: 1199961 (C4 (Web Text))

Max Activating Token Index: 958

Text #1

Max Range: 1.8185. Min Range: -1.8185

Max Act: 1.8015. Min Act: -0.0000

Data Index: 599185 (C4 (Web Text))

Max Activating Token Index: 952

Text #2

Max Range: 1.8185. Min Range: -1.8185

Max Act: 1.7473. Min Act: -0.0000

Data Index: 1062303 (C4 (Web Text))

Max Activating Token Index: 1008

Text #3

Max Range: 1.8185. Min Range: -1.8185

Max Act: 1.6238. Min Act: -0.0000

Data Index: 1609682 (Python Code)

Max Activating Token Index: 139

Text #4

Max Range: 1.8185. Min Range: -1.8185

Max Act: 1.6287. Min Act: -0.0000

Data Index: 904491 (C4 (Web Text))

Max Activating Token Index: 819

Text #5

Max Range: 1.8185. Min Range: -1.8185

Max Act: 1.6373. Min Act: -0.0000

Data Index: 610273 (C4 (Web Text))

Max Activating Token Index: 651

Text #6

Max Range: 1.8185. Min Range: -1.8185

Max Act: 1.6079. Min Act: -0.0000

Data Index: 986754 (C4 (Web Text))

Max Activating Token Index: 139

Text #7

Max Range: 1.8185. Min Range: -1.8185

Max Act: 1.6001. Min Act: -0.0000

Data Index: 798015 (C4 (Web Text))

Max Activating Token Index: 8

Text #8

Max Range: 1.8185. Min Range: -1.8185

Max Act: 1.6786. Min Act: -0.0000

Data Index: 600415 (C4 (Web Text))

Max Activating Token Index: 742

Text #9

Max Range: 1.8185. Min Range: -1.8185

Max Act: 1.5326. Min Act: -0.0000

Data Index: 884188 (C4 (Web Text))

Max Activating Token Index: 812

Text #10

Max Range: 1.8185. Min Range: -1.8185

Max Act: 1.5415. Min Act: -0.0000

Data Index: 685662 (C4 (Web Text))

Max Activating Token Index: 281

Text #11

Max Range: 1.8185. Min Range: -1.8185

Max Act: 1.5711. Min Act: -0.0000

Data Index: 480033 (C4 (Web Text))

Max Activating Token Index: 950

Text #12

Max Range: 1.8185. Min Range: -1.8185

Max Act: 1.5131. Min Act: -0.0000

Data Index: 941400 (C4 (Web Text))

Max Activating Token Index: 520

Text #13

Max Range: 1.8185. Min Range: -1.8185

Max Act: 1.5951. Min Act: -0.0000

Data Index: 173568 (C4 (Web Text))

Max Activating Token Index: 905

Text #14

Max Range: 1.8185. Min Range: -1.8185

Max Act: 1.5054. Min Act: -0.0000

Data Index: 606841 (C4 (Web Text))

Max Activating Token Index: 870

Text #15

Max Range: 1.8185. Min Range: -1.8185

Max Act: 1.5560. Min Act: -0.0000

Data Index: 1101470 (C4 (Web Text))

Max Activating Token Index: 324

Text #16

Max Range: 1.8185. Min Range: -1.8185

Max Act: 1.5850. Min Act: -0.0000

Data Index: 1330389 (C4 (Web Text))

Max Activating Token Index: 884

Text #17

Max Range: 1.8185. Min Range: -1.8185

Max Act: 1.4443. Min Act: -0.0000

Data Index: 851341 (C4 (Web Text))

Max Activating Token Index: 537

Text #18

Max Range: 1.8185. Min Range: -1.8185

Max Act: 1.5451. Min Act: -0.0000

Data Index: 131837 (C4 (Web Text))

Max Activating Token Index: 995

Text #19

Max Range: 1.8185. Min Range: -1.8185

Max Act: 1.5569. Min Act: -0.0000

Data Index: 174725 (C4 (Web Text))

Max Activating Token Index: 865