Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4967 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1379. Min Range: -6.1379
Max Act: 6.1379. Min Act: -0.1700
Data Index: 4423541 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1379. Min Range: -6.1379
Max Act: 6.0754. Min Act: -0.1700
Data Index: 1363845 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1379. Min Range: -6.1379
Max Act: 5.7629. Min Act: -0.1700
Data Index: 4515858 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1379. Min Range: -6.1379
Max Act: 5.7316. Min Act: -0.1700
Data Index: 2354569 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1379. Min Range: -6.1379
Max Act: 5.6066. Min Act: -0.1700
Data Index: 3398962 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1379. Min Range: -6.1379
Max Act: 5.5754. Min Act: -0.1700
Data Index: 7475583 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1379. Min Range: -6.1379
Max Act: 5.5754. Min Act: -0.1700
Data Index: 2508805 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1379. Min Range: -6.1379
Max Act: 5.5754. Min Act: -0.1700
Data Index: 4433772 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1379. Min Range: -6.1379
Max Act: 5.5754. Min Act: -0.1700
Data Index: 6199659 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1379. Min Range: -6.1379
Max Act: 5.5754. Min Act: -0.1700
Data Index: 6384185 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1379. Min Range: -6.1379
Max Act: 5.5129. Min Act: -0.1700
Data Index: 7693849 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1379. Min Range: -6.1379
Max Act: 5.5129. Min Act: -0.1700
Data Index: 3252256 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1379. Min Range: -6.1379
Max Act: 5.5129. Min Act: -0.1700
Data Index: 7069884 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1379. Min Range: -6.1379
Max Act: 5.5129. Min Act: -0.1700
Data Index: 6016811 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1379. Min Range: -6.1379
Max Act: 5.4816. Min Act: -0.1700
Data Index: 8349377 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1379. Min Range: -6.1379
Max Act: 5.4816. Min Act: -0.1700
Data Index: 3818074 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1379. Min Range: -6.1379
Max Act: 5.4504. Min Act: -0.1700
Data Index: 4133919 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1379. Min Range: -6.1379
Max Act: 5.4816. Min Act: -0.1700
Data Index: 2614188 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1379. Min Range: -6.1379
Max Act: 5.4504. Min Act: -0.1700
Data Index: 4580234 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1379. Min Range: -6.1379
Max Act: 5.4191. Min Act: -0.1700
Data Index: 1043555 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #19