Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4775 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7608. Min Range: -5.7608
Max Act: 5.7608. Min Act: -0.1700
Data Index: 7655732 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7608. Min Range: -5.7608
Max Act: 5.3233. Min Act: -0.1700
Data Index: 4192485 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7608. Min Range: -5.7608
Max Act: 5.3233. Min Act: -0.1700
Data Index: 4589188 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7608. Min Range: -5.7608
Max Act: 5.2921. Min Act: -0.1700
Data Index: 8641427 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7608. Min Range: -5.7608
Max Act: 5.3233. Min Act: -0.1700
Data Index: 6648805 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7608. Min Range: -5.7608
Max Act: 5.2296. Min Act: -0.1700
Data Index: 1858722 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7608. Min Range: -5.7608
Max Act: 5.2296. Min Act: -0.1700
Data Index: 4765331 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7608. Min Range: -5.7608
Max Act: 5.2296. Min Act: -0.1700
Data Index: 1197650 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7608. Min Range: -5.7608
Max Act: 5.2296. Min Act: -0.1700
Data Index: 7098819 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7608. Min Range: -5.7608
Max Act: 5.1671. Min Act: -0.1700
Data Index: 1530102 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7608. Min Range: -5.7608
Max Act: 5.1671. Min Act: -0.1700
Data Index: 224429 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7608. Min Range: -5.7608
Max Act: 5.1671. Min Act: -0.1700
Data Index: 1372535 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7608. Min Range: -5.7608
Max Act: 5.1358. Min Act: -0.1700
Data Index: 6356602 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7608. Min Range: -5.7608
Max Act: 5.1358. Min Act: -0.1700
Data Index: 3160906 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7608. Min Range: -5.7608
Max Act: 5.1358. Min Act: -0.1700
Data Index: 8148483 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7608. Min Range: -5.7608
Max Act: 5.1046. Min Act: -0.1700
Data Index: 5469713 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7608. Min Range: -5.7608
Max Act: 5.1046. Min Act: -0.1700
Data Index: 1561413 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7608. Min Range: -5.7608
Max Act: 5.1358. Min Act: -0.1700
Data Index: 6438620 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7608. Min Range: -5.7608
Max Act: 5.1046. Min Act: -0.1700
Data Index: 5969083 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7608. Min Range: -5.7608
Max Act: 5.0733. Min Act: -0.1700
Data Index: 7784024 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #19