Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 138 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.1973. Min Range: -3.1973

Max Act: 3.1973. Min Act: -0.1700

Data Index: 157792 (C4 (Web Text))

Max Activating Token Index: 40

Text #1

Max Range: 3.1973. Min Range: -3.1973

Max Act: 3.1028. Min Act: -0.1700

Data Index: 1086113 (C4 (Web Text))

Max Activating Token Index: 65

Text #2

Max Range: 3.1973. Min Range: -3.1973

Max Act: 3.1343. Min Act: -0.1700

Data Index: 281341 (C4 (Web Text))

Max Activating Token Index: 811

Text #3

Max Range: 3.1973. Min Range: -3.1973

Max Act: 3.0870. Min Act: -0.1700

Data Index: 1216500 (C4 (Web Text))

Max Activating Token Index: 740

Text #4

Max Range: 3.1973. Min Range: -3.1973

Max Act: 3.0713. Min Act: -0.1700

Data Index: 985606 (C4 (Web Text))

Max Activating Token Index: 975

Text #5

Max Range: 3.1973. Min Range: -3.1973

Max Act: 3.0870. Min Act: -0.1700

Data Index: 993525 (C4 (Web Text))

Max Activating Token Index: 876

Text #6

Max Range: 3.1973. Min Range: -3.1973

Max Act: 3.0713. Min Act: -0.1700

Data Index: 276538 (C4 (Web Text))

Max Activating Token Index: 117

Text #7

Max Range: 3.1973. Min Range: -3.1973

Max Act: 3.0555. Min Act: -0.1700

Data Index: 61074 (C4 (Web Text))

Max Activating Token Index: 202

Text #8

Max Range: 3.1973. Min Range: -3.1973

Max Act: 3.0397. Min Act: -0.1700

Data Index: 1202540 (C4 (Web Text))

Max Activating Token Index: 452

Text #9

Max Range: 3.1973. Min Range: -3.1973

Max Act: 3.0239. Min Act: -0.1700

Data Index: 1306026 (C4 (Web Text))

Max Activating Token Index: 586

Text #10

Max Range: 3.1973. Min Range: -3.1973

Max Act: 3.0397. Min Act: -0.1700

Data Index: 258074 (C4 (Web Text))

Max Activating Token Index: 799

Text #11

Max Range: 3.1973. Min Range: -3.1973

Max Act: 3.0239. Min Act: -0.1700

Data Index: 799865 (C4 (Web Text))

Max Activating Token Index: 669

Text #12

Max Range: 3.1973. Min Range: -3.1973

Max Act: 3.0239. Min Act: -0.1700

Data Index: 126605 (C4 (Web Text))

Max Activating Token Index: 579

Text #13

Max Range: 3.1973. Min Range: -3.1973

Max Act: 3.0397. Min Act: -0.1700

Data Index: 353233 (C4 (Web Text))

Max Activating Token Index: 533

Text #14

Max Range: 3.1973. Min Range: -3.1973

Max Act: 3.0081. Min Act: -0.1700

Data Index: 1187913 (C4 (Web Text))

Max Activating Token Index: 131

Text #15

Max Range: 3.1973. Min Range: -3.1973

Max Act: 3.0239. Min Act: -0.1700

Data Index: 1138005 (C4 (Web Text))

Max Activating Token Index: 890

Text #16

Max Range: 3.1973. Min Range: -3.1973

Max Act: 3.0239. Min Act: -0.1700

Data Index: 1328305 (C4 (Web Text))

Max Activating Token Index: 823

Text #17

Max Range: 3.1973. Min Range: -3.1973

Max Act: 3.0239. Min Act: -0.1700

Data Index: 1027939 (C4 (Web Text))

Max Activating Token Index: 824

Text #18

Max Range: 3.1973. Min Range: -3.1973

Max Act: 3.0239. Min Act: -0.1700

Data Index: 634879 (C4 (Web Text))

Max Activating Token Index: 31

Text #19

Max Range: 3.1973. Min Range: -3.1973

Max Act: 3.0239. Min Act: -0.1700

Data Index: 813317 (C4 (Web Text))

Max Activating Token Index: 927