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

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

Neuron 3 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: 3.3966. Min Range: -3.3966

Max Act: 3.3966. Min Act: -0.1700

Data Index: 797013 (C4 (Web Text))

Max Activating Token Index: 37

Text #1

Max Range: 3.3966. Min Range: -3.3966

Max Act: 3.3181. Min Act: -0.1700

Data Index: 195856 (C4 (Web Text))

Max Activating Token Index: 114

Text #2

Max Range: 3.3966. Min Range: -3.3966

Max Act: 3.3024. Min Act: -0.1700

Data Index: 882845 (C4 (Web Text))

Max Activating Token Index: 16

Text #3

Max Range: 3.3966. Min Range: -3.3966

Max Act: 3.2867. Min Act: -0.1700

Data Index: 557586 (C4 (Web Text))

Max Activating Token Index: 56

Text #4

Max Range: 3.3966. Min Range: -3.3966

Max Act: 3.2867. Min Act: -0.1700

Data Index: 397534 (C4 (Web Text))

Max Activating Token Index: 819

Text #5

Max Range: 3.3966. Min Range: -3.3966

Max Act: 3.2710. Min Act: -0.1700

Data Index: 815218 (C4 (Web Text))

Max Activating Token Index: 503

Text #6

Max Range: 3.3966. Min Range: -3.3966

Max Act: 3.2867. Min Act: -0.1700

Data Index: 186608 (C4 (Web Text))

Max Activating Token Index: 55

Text #7

Max Range: 3.3966. Min Range: -3.3966

Max Act: 3.2867. Min Act: -0.1700

Data Index: 158856 (C4 (Web Text))

Max Activating Token Index: 18

Text #8

Max Range: 3.3966. Min Range: -3.3966

Max Act: 3.2710. Min Act: -0.1700

Data Index: 520995 (C4 (Web Text))

Max Activating Token Index: 37

Text #9

Max Range: 3.3966. Min Range: -3.3966

Max Act: 3.2710. Min Act: -0.1700

Data Index: 677323 (C4 (Web Text))

Max Activating Token Index: 71

Text #10

Max Range: 3.3966. Min Range: -3.3966

Max Act: 3.2553. Min Act: -0.1700

Data Index: 1075039 (C4 (Web Text))

Max Activating Token Index: 78

Text #11

Max Range: 3.3966. Min Range: -3.3966

Max Act: 3.2553. Min Act: -0.1700

Data Index: 1109839 (C4 (Web Text))

Max Activating Token Index: 218

Text #12

Max Range: 3.3966. Min Range: -3.3966

Max Act: 3.2553. Min Act: -0.1700

Data Index: 657933 (C4 (Web Text))

Max Activating Token Index: 781

Text #13

Max Range: 3.3966. Min Range: -3.3966

Max Act: 3.2553. Min Act: -0.1700

Data Index: 679702 (C4 (Web Text))

Max Activating Token Index: 841

Text #14

Max Range: 3.3966. Min Range: -3.3966

Max Act: 3.2396. Min Act: -0.1700

Data Index: 1013218 (C4 (Web Text))

Max Activating Token Index: 20

Text #15

Max Range: 3.3966. Min Range: -3.3966

Max Act: 3.2396. Min Act: -0.1700

Data Index: 75456 (C4 (Web Text))

Max Activating Token Index: 15

Text #16

Max Range: 3.3966. Min Range: -3.3966

Max Act: 3.2396. Min Act: -0.1700

Data Index: 1143217 (C4 (Web Text))

Max Activating Token Index: 653

Text #17

Max Range: 3.3966. Min Range: -3.3966

Max Act: 3.2396. Min Act: -0.1700

Data Index: 991134 (C4 (Web Text))

Max Activating Token Index: 121

Text #18

Max Range: 3.3966. Min Range: -3.3966

Max Act: 3.2396. Min Act: -0.1700

Data Index: 963023 (C4 (Web Text))

Max Activating Token Index: 945

Text #19

Max Range: 3.3966. Min Range: -3.3966

Max Act: 3.2239. Min Act: -0.1700

Data Index: 700423 (C4 (Web Text))

Max Activating Token Index: 4