Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2803 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5556. Min Range: -6.5556
Max Act: 6.5556. Min Act: -0.1700
Data Index: 7309010 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5556. Min Range: -6.5556
Max Act: 6.5243. Min Act: -0.1700
Data Index: 8466838 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5556. Min Range: -6.5556
Max Act: 6.5243. Min Act: -0.1700
Data Index: 4063229 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5556. Min Range: -6.5556
Max Act: 6.4931. Min Act: -0.1700
Data Index: 7836500 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5556. Min Range: -6.5556
Max Act: 6.3681. Min Act: -0.1700
Data Index: 3091020 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5556. Min Range: -6.5556
Max Act: 6.3056. Min Act: -0.1700
Data Index: 4950572 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5556. Min Range: -6.5556
Max Act: 6.3056. Min Act: -0.1700
Data Index: 7791924 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5556. Min Range: -6.5556
Max Act: 6.2743. Min Act: -0.1700
Data Index: 5875964 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5556. Min Range: -6.5556
Max Act: 6.3056. Min Act: -0.1700
Data Index: 2154797 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5556. Min Range: -6.5556
Max Act: 6.2743. Min Act: -0.1700
Data Index: 8285631 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5556. Min Range: -6.5556
Max Act: 6.2431. Min Act: -0.1700
Data Index: 1213671 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5556. Min Range: -6.5556
Max Act: 6.2118. Min Act: -0.1700
Data Index: 3577306 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5556. Min Range: -6.5556
Max Act: 6.2118. Min Act: -0.1700
Data Index: 2317186 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5556. Min Range: -6.5556
Max Act: 6.2118. Min Act: -0.1700
Data Index: 8466839 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5556. Min Range: -6.5556
Max Act: 6.2118. Min Act: -0.1700
Data Index: 4692767 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5556. Min Range: -6.5556
Max Act: 6.1806. Min Act: -0.1700
Data Index: 8721261 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5556. Min Range: -6.5556
Max Act: 6.1806. Min Act: -0.1700
Data Index: 3833199 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5556. Min Range: -6.5556
Max Act: 6.1493. Min Act: -0.1700
Data Index: 3357069 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5556. Min Range: -6.5556
Max Act: 6.1493. Min Act: -0.1700
Data Index: 3580553 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5556. Min Range: -6.5556
Max Act: 6.1181. Min Act: -0.1700
Data Index: 8688391 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #19