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

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

Neuron 3744 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.1322. Min Act: -0.0001

Data Index: 1616497 (Python Code)

Max Activating Token Index: 680

Text #1

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.1227. Min Act: -0.0001

Data Index: 191009 (C4 (Web Text))

Max Activating Token Index: 750

Text #2

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.1248. Min Act: -0.0001

Data Index: 432595 (C4 (Web Text))

Max Activating Token Index: 879

Text #3

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.1141. Min Act: -0.0001

Data Index: 581173 (C4 (Web Text))

Max Activating Token Index: 14

Text #4

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.1075. Min Act: -0.0001

Data Index: 150637 (C4 (Web Text))

Max Activating Token Index: 472

Text #5

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.1025. Min Act: -0.0001

Data Index: 824687 (C4 (Web Text))

Max Activating Token Index: 694

Text #6

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.1044. Min Act: -0.0001

Data Index: 683031 (C4 (Web Text))

Max Activating Token Index: 16

Text #7

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.0888. Min Act: -0.0001

Data Index: 404052 (C4 (Web Text))

Max Activating Token Index: 797

Text #8

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.0966. Min Act: -0.0001

Data Index: 1194705 (C4 (Web Text))

Max Activating Token Index: 518

Text #9

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.1001. Min Act: -0.0001

Data Index: 272772 (C4 (Web Text))

Max Activating Token Index: 246

Text #10

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.0964. Min Act: -0.0001

Data Index: 1266361 (C4 (Web Text))

Max Activating Token Index: 871

Text #11

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.0950. Min Act: -0.0001

Data Index: 1124428 (C4 (Web Text))

Max Activating Token Index: 190

Text #12

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.0936. Min Act: -0.0001

Data Index: 1053908 (C4 (Web Text))

Max Activating Token Index: 562

Text #13

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.0982. Min Act: -0.0001

Data Index: 793803 (C4 (Web Text))

Max Activating Token Index: 888

Text #14

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.0901. Min Act: -0.0001

Data Index: 309336 (C4 (Web Text))

Max Activating Token Index: 113

Text #15

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.0996. Min Act: -0.0001

Data Index: 1203524 (C4 (Web Text))

Max Activating Token Index: 139

Text #16

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.0863. Min Act: -0.0001

Data Index: 334501 (C4 (Web Text))

Max Activating Token Index: 866

Text #17

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.0946. Min Act: -0.0001

Data Index: 798231 (C4 (Web Text))

Max Activating Token Index: 326

Text #18

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.0993. Min Act: -0.0001

Data Index: 753040 (C4 (Web Text))

Max Activating Token Index: 55

Text #19

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.0854. Min Act: -0.0001

Data Index: 430581 (C4 (Web Text))

Max Activating Token Index: 731