Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2896 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2007. Min Range: -7.2007
Max Act: 7.2007. Min Act: -0.1700
Data Index: 4291099 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2007. Min Range: -7.2007
Max Act: 7.0757. Min Act: -0.1700
Data Index: 7041760 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2007. Min Range: -7.2007
Max Act: 7.0757. Min Act: -0.1700
Data Index: 4296001 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2007. Min Range: -7.2007
Max Act: 7.0132. Min Act: -0.1700
Data Index: 8511696 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2007. Min Range: -7.2007
Max Act: 6.9820. Min Act: -0.1700
Data Index: 4575340 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2007. Min Range: -7.2007
Max Act: 6.9820. Min Act: -0.1700
Data Index: 4390322 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2007. Min Range: -7.2007
Max Act: 6.9507. Min Act: -0.1700
Data Index: 5803837 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2007. Min Range: -7.2007
Max Act: 6.8882. Min Act: -0.1700
Data Index: 2031454 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2007. Min Range: -7.2007
Max Act: 6.7945. Min Act: -0.1700
Data Index: 2169619 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2007. Min Range: -7.2007
Max Act: 6.7945. Min Act: -0.1700
Data Index: 1668763 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2007. Min Range: -7.2007
Max Act: 6.7320. Min Act: -0.1700
Data Index: 6843179 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2007. Min Range: -7.2007
Max Act: 6.7320. Min Act: -0.1700
Data Index: 2155566 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2007. Min Range: -7.2007
Max Act: 6.7320. Min Act: -0.1700
Data Index: 8673045 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2007. Min Range: -7.2007
Max Act: 6.7007. Min Act: -0.1700
Data Index: 7621065 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2007. Min Range: -7.2007
Max Act: 6.7007. Min Act: -0.1700
Data Index: 4872042 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2007. Min Range: -7.2007
Max Act: 6.6695. Min Act: -0.1700
Data Index: 807820 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2007. Min Range: -7.2007
Max Act: 6.6695. Min Act: -0.1700
Data Index: 4227738 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2007. Min Range: -7.2007
Max Act: 6.6695. Min Act: -0.1700
Data Index: 4798128 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2007. Min Range: -7.2007
Max Act: 6.6695. Min Act: -0.1700
Data Index: 4829106 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2007. Min Range: -7.2007
Max Act: 6.6695. Min Act: -0.1700
Data Index: 2266793 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #19