Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3940 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3127. Min Range: -7.3127
Max Act: 7.3127. Min Act: -0.1700
Data Index: 899979 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3127. Min Range: -7.3127
Max Act: 7.2189. Min Act: -0.1700
Data Index: 982184 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3127. Min Range: -7.3127
Max Act: 7.1252. Min Act: -0.1700
Data Index: 1880799 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3127. Min Range: -7.3127
Max Act: 7.1564. Min Act: -0.1700
Data Index: 5027820 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3127. Min Range: -7.3127
Max Act: 7.1252. Min Act: -0.1700
Data Index: 5518703 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3127. Min Range: -7.3127
Max Act: 7.0939. Min Act: -0.1700
Data Index: 4533125 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3127. Min Range: -7.3127
Max Act: 7.0939. Min Act: -0.1700
Data Index: 3711121 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3127. Min Range: -7.3127
Max Act: 7.0939. Min Act: -0.1700
Data Index: 698447 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3127. Min Range: -7.3127
Max Act: 7.0314. Min Act: -0.1700
Data Index: 1880800 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3127. Min Range: -7.3127
Max Act: 7.0002. Min Act: -0.1700
Data Index: 6251550 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3127. Min Range: -7.3127
Max Act: 7.0002. Min Act: -0.1700
Data Index: 7641977 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3127. Min Range: -7.3127
Max Act: 6.9689. Min Act: -0.1700
Data Index: 234389 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3127. Min Range: -7.3127
Max Act: 6.9377. Min Act: -0.1700
Data Index: 7434259 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3127. Min Range: -7.3127
Max Act: 6.9377. Min Act: -0.1700
Data Index: 8771692 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3127. Min Range: -7.3127
Max Act: 6.9064. Min Act: -0.1700
Data Index: 547989 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3127. Min Range: -7.3127
Max Act: 6.9064. Min Act: -0.1700
Data Index: 1989870 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3127. Min Range: -7.3127
Max Act: 6.9064. Min Act: -0.1700
Data Index: 2953124 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3127. Min Range: -7.3127
Max Act: 6.9064. Min Act: -0.1700
Data Index: 1633602 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3127. Min Range: -7.3127
Max Act: 6.9064. Min Act: -0.1700
Data Index: 2635179 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3127. Min Range: -7.3127
Max Act: 6.8752. Min Act: -0.1700
Data Index: 1007155 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #19