Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 908 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.1034. Min Range: -3.1034

Max Act: 3.1034. Min Act: -0.1700

Data Index: 312236 (C4 (Web Text))

Max Activating Token Index: 11

Text #1

Max Range: 3.1034. Min Range: -3.1034

Max Act: 3.0718. Min Act: -0.1700

Data Index: 800207 (C4 (Web Text))

Max Activating Token Index: 785

Text #2

Max Range: 3.1034. Min Range: -3.1034

Max Act: 3.0876. Min Act: -0.1700

Data Index: 982694 (C4 (Web Text))

Max Activating Token Index: 973

Text #3

Max Range: 3.1034. Min Range: -3.1034

Max Act: 3.0560. Min Act: -0.1700

Data Index: 1212853 (C4 (Web Text))

Max Activating Token Index: 254

Text #4

Max Range: 3.1034. Min Range: -3.1034

Max Act: 3.0560. Min Act: -0.1700

Data Index: 118302 (C4 (Web Text))

Max Activating Token Index: 7

Text #5

Max Range: 3.1034. Min Range: -3.1034

Max Act: 3.0245. Min Act: -0.1700

Data Index: 503773 (C4 (Web Text))

Max Activating Token Index: 3

Text #6

Max Range: 3.1034. Min Range: -3.1034

Max Act: 3.0402. Min Act: -0.1700

Data Index: 1149194 (C4 (Web Text))

Max Activating Token Index: 93

Text #7

Max Range: 3.1034. Min Range: -3.1034

Max Act: 3.0402. Min Act: -0.1700

Data Index: 819836 (C4 (Web Text))

Max Activating Token Index: 14

Text #8

Max Range: 3.1034. Min Range: -3.1034

Max Act: 3.0245. Min Act: -0.1700

Data Index: 117447 (C4 (Web Text))

Max Activating Token Index: 921

Text #9

Max Range: 3.1034. Min Range: -3.1034

Max Act: 3.0245. Min Act: -0.1700

Data Index: 863749 (C4 (Web Text))

Max Activating Token Index: 56

Text #10

Max Range: 3.1034. Min Range: -3.1034

Max Act: 3.0245. Min Act: -0.1700

Data Index: 1064409 (C4 (Web Text))

Max Activating Token Index: 53

Text #11

Max Range: 3.1034. Min Range: -3.1034

Max Act: 3.0245. Min Act: -0.1700

Data Index: 953354 (C4 (Web Text))

Max Activating Token Index: 3

Text #12

Max Range: 3.1034. Min Range: -3.1034

Max Act: 3.0245. Min Act: -0.1700

Data Index: 670641 (C4 (Web Text))

Max Activating Token Index: 943

Text #13

Max Range: 3.1034. Min Range: -3.1034

Max Act: 2.9928. Min Act: -0.1700

Data Index: 908529 (C4 (Web Text))

Max Activating Token Index: 14

Text #14

Max Range: 3.1034. Min Range: -3.1034

Max Act: 2.9928. Min Act: -0.1700

Data Index: 341707 (C4 (Web Text))

Max Activating Token Index: 736

Text #15

Max Range: 3.1034. Min Range: -3.1034

Max Act: 2.9928. Min Act: -0.1700

Data Index: 356459 (C4 (Web Text))

Max Activating Token Index: 263

Text #16

Max Range: 3.1034. Min Range: -3.1034

Max Act: 2.9928. Min Act: -0.1700

Data Index: 453277 (C4 (Web Text))

Max Activating Token Index: 93

Text #17

Max Range: 3.1034. Min Range: -3.1034

Max Act: 2.9770. Min Act: -0.1700

Data Index: 416452 (C4 (Web Text))

Max Activating Token Index: 46

Text #18

Max Range: 3.1034. Min Range: -3.1034

Max Act: 2.9928. Min Act: -0.1700

Data Index: 1278069 (C4 (Web Text))

Max Activating Token Index: 402

Text #19

Max Range: 3.1034. Min Range: -3.1034

Max Act: 2.9928. Min Act: -0.1700

Data Index: 964856 (C4 (Web Text))

Max Activating Token Index: 29