Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1630 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.6941. Min Range: -2.6941
Max Act: 2.6941. Min Act: -0.1700
Data Index: 1599818 (Python Code)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6941. Min Range: -2.6941
Max Act: 2.6941. Min Act: -0.1700
Data Index: 354900 (C4 (Web Text))
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6941. Min Range: -2.6941
Max Act: 2.6460. Min Act: -0.1700
Data Index: 1519415 (Python Code)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6941. Min Range: -2.6941
Max Act: 2.6139. Min Act: -0.1700
Data Index: 467973 (C4 (Web Text))
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6941. Min Range: -2.6941
Max Act: 2.6460. Min Act: -0.1700
Data Index: 1637040 (Python Code)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6941. Min Range: -2.6941
Max Act: 2.6300. Min Act: -0.1700
Data Index: 945853 (C4 (Web Text))
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6941. Min Range: -2.6941
Max Act: 2.6300. Min Act: -0.1700
Data Index: 310452 (C4 (Web Text))
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6941. Min Range: -2.6941
Max Act: 2.6139. Min Act: -0.1700
Data Index: 1431649 (Python Code)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6941. Min Range: -2.6941
Max Act: 2.5978. Min Act: -0.1700
Data Index: 928084 (C4 (Web Text))
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6941. Min Range: -2.6941
Max Act: 2.5978. Min Act: -0.1700
Data Index: 201615 (C4 (Web Text))
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6941. Min Range: -2.6941
Max Act: 2.5978. Min Act: -0.1700
Data Index: 697723 (C4 (Web Text))
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6941. Min Range: -2.6941
Max Act: 2.5817. Min Act: -0.1700
Data Index: 1513598 (Python Code)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6941. Min Range: -2.6941
Max Act: 2.5817. Min Act: -0.1700
Data Index: 1521741 (Python Code)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6941. Min Range: -2.6941
Max Act: 2.5817. Min Act: -0.1700
Data Index: 136095 (C4 (Web Text))
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6941. Min Range: -2.6941
Max Act: 2.5817. Min Act: -0.1700
Data Index: 1226800 (C4 (Web Text))
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6941. Min Range: -2.6941
Max Act: 2.5656. Min Act: -0.1700
Data Index: 1622144 (Python Code)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6941. Min Range: -2.6941
Max Act: 2.5656. Min Act: -0.1700
Data Index: 1655792 (Python Code)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6941. Min Range: -2.6941
Max Act: 2.5817. Min Act: -0.1700
Data Index: 296920 (C4 (Web Text))
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6941. Min Range: -2.6941
Max Act: 2.5495. Min Act: -0.1700
Data Index: 718309 (C4 (Web Text))
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6941. Min Range: -2.6941
Max Act: 2.5817. Min Act: -0.1700
Data Index: 189526 (C4 (Web Text))
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #19