Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1888 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7629. Min Range: -6.7629
Max Act: 6.7629. Min Act: -0.1700
Data Index: 2651333 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7629. Min Range: -6.7629
Max Act: 6.5129. Min Act: -0.1700
Data Index: 1696543 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7629. Min Range: -6.7629
Max Act: 6.4192. Min Act: -0.1700
Data Index: 5287640 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7629. Min Range: -6.7629
Max Act: 6.3879. Min Act: -0.1700
Data Index: 6308401 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7629. Min Range: -6.7629
Max Act: 6.3567. Min Act: -0.1700
Data Index: 4332276 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7629. Min Range: -6.7629
Max Act: 6.3254. Min Act: -0.1700
Data Index: 5648808 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7629. Min Range: -6.7629
Max Act: 6.2629. Min Act: -0.1700
Data Index: 317099 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7629. Min Range: -6.7629
Max Act: 6.2317. Min Act: -0.1700
Data Index: 5835853 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7629. Min Range: -6.7629
Max Act: 6.2317. Min Act: -0.1700
Data Index: 2514457 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7629. Min Range: -6.7629
Max Act: 6.2004. Min Act: -0.1700
Data Index: 8328310 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7629. Min Range: -6.7629
Max Act: 6.2004. Min Act: -0.1700
Data Index: 6964108 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7629. Min Range: -6.7629
Max Act: 6.1692. Min Act: -0.1700
Data Index: 4921195 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7629. Min Range: -6.7629
Max Act: 6.1692. Min Act: -0.1700
Data Index: 2681037 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7629. Min Range: -6.7629
Max Act: 6.1692. Min Act: -0.1700
Data Index: 7331589 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7629. Min Range: -6.7629
Max Act: 6.1692. Min Act: -0.1700
Data Index: 3755914 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7629. Min Range: -6.7629
Max Act: 6.1379. Min Act: -0.1700
Data Index: 2754450 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7629. Min Range: -6.7629
Max Act: 6.1379. Min Act: -0.1700
Data Index: 8536212 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7629. Min Range: -6.7629
Max Act: 6.1379. Min Act: -0.1700
Data Index: 6260925 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7629. Min Range: -6.7629
Max Act: 6.1379. Min Act: -0.1700
Data Index: 7734545 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7629. Min Range: -6.7629
Max Act: 6.1067. Min Act: -0.1700
Data Index: 2965802 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #19