Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2506 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3191. Min Range: -6.3191
Max Act: 6.3191. Min Act: -0.1700
Data Index: 1801593 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3191. Min Range: -6.3191
Max Act: 6.2254. Min Act: -0.1700
Data Index: 546107 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3191. Min Range: -6.3191
Max Act: 6.1941. Min Act: -0.1700
Data Index: 3480722 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3191. Min Range: -6.3191
Max Act: 6.1316. Min Act: -0.1700
Data Index: 8782401 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3191. Min Range: -6.3191
Max Act: 6.1316. Min Act: -0.1700
Data Index: 1554082 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3191. Min Range: -6.3191
Max Act: 6.0379. Min Act: -0.1700
Data Index: 4500690 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3191. Min Range: -6.3191
Max Act: 6.0066. Min Act: -0.1700
Data Index: 7760649 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3191. Min Range: -6.3191
Max Act: 6.0066. Min Act: -0.1700
Data Index: 5636680 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3191. Min Range: -6.3191
Max Act: 5.9754. Min Act: -0.1700
Data Index: 2418845 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3191. Min Range: -6.3191
Max Act: 5.9754. Min Act: -0.1700
Data Index: 8699582 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3191. Min Range: -6.3191
Max Act: 5.9441. Min Act: -0.1700
Data Index: 1387847 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3191. Min Range: -6.3191
Max Act: 5.9441. Min Act: -0.1700
Data Index: 250386 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3191. Min Range: -6.3191
Max Act: 5.9754. Min Act: -0.1700
Data Index: 1180153 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3191. Min Range: -6.3191
Max Act: 5.9441. Min Act: -0.1700
Data Index: 238802 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3191. Min Range: -6.3191
Max Act: 5.9129. Min Act: -0.1700
Data Index: 124629 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3191. Min Range: -6.3191
Max Act: 5.9441. Min Act: -0.1700
Data Index: 1704412 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3191. Min Range: -6.3191
Max Act: 5.9129. Min Act: -0.1700
Data Index: 710804 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3191. Min Range: -6.3191
Max Act: 5.8816. Min Act: -0.1700
Data Index: 1531576 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3191. Min Range: -6.3191
Max Act: 5.8816. Min Act: -0.1700
Data Index: 479915 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3191. Min Range: -6.3191
Max Act: 5.8816. Min Act: -0.1700
Data Index: 3836245 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #19