Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2627 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6314. Min Range: -5.6314
Max Act: 5.6314. Min Act: -0.1700
Data Index: 6488712 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6314. Min Range: -5.6314
Max Act: 5.4439. Min Act: -0.1700
Data Index: 7919556 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6314. Min Range: -5.6314
Max Act: 5.0689. Min Act: -0.1700
Data Index: 232851 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6314. Min Range: -5.6314
Max Act: 5.0377. Min Act: -0.1700
Data Index: 8767042 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6314. Min Range: -5.6314
Max Act: 5.0377. Min Act: -0.1700
Data Index: 1546592 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6314. Min Range: -5.6314
Max Act: 5.0064. Min Act: -0.1700
Data Index: 6419710 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6314. Min Range: -5.6314
Max Act: 5.0377. Min Act: -0.1700
Data Index: 6254605 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6314. Min Range: -5.6314
Max Act: 5.0064. Min Act: -0.1700
Data Index: 4323867 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6314. Min Range: -5.6314
Max Act: 5.0064. Min Act: -0.1700
Data Index: 4031770 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6314. Min Range: -5.6314
Max Act: 4.9752. Min Act: -0.1700
Data Index: 4834497 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6314. Min Range: -5.6314
Max Act: 4.9439. Min Act: -0.1700
Data Index: 7551856 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6314. Min Range: -5.6314
Max Act: 4.8814. Min Act: -0.1700
Data Index: 2196528 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6314. Min Range: -5.6314
Max Act: 4.9127. Min Act: -0.1700
Data Index: 4279445 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6314. Min Range: -5.6314
Max Act: 4.9127. Min Act: -0.1700
Data Index: 3996764 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6314. Min Range: -5.6314
Max Act: 4.9127. Min Act: -0.1700
Data Index: 5275150 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6314. Min Range: -5.6314
Max Act: 4.8814. Min Act: -0.1700
Data Index: 7772251 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6314. Min Range: -5.6314
Max Act: 4.8502. Min Act: -0.1700
Data Index: 513573 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6314. Min Range: -5.6314
Max Act: 4.8814. Min Act: -0.1700
Data Index: 4713477 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6314. Min Range: -5.6314
Max Act: 4.8814. Min Act: -0.1700
Data Index: 3033818 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6314. Min Range: -5.6314
Max Act: 4.8814. Min Act: -0.1700
Data Index: 6383761 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #19