Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4617 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1752. Min Range: -3.1752
Max Act: 3.1752. Min Act: -0.1700
Data Index: 7076024 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1752. Min Range: -3.1752
Max Act: 3.1123. Min Act: -0.1700
Data Index: 8226205 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1752. Min Range: -3.1752
Max Act: 3.1123. Min Act: -0.1700
Data Index: 2934798 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1752. Min Range: -3.1752
Max Act: 3.0965. Min Act: -0.1700
Data Index: 1344930 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1752. Min Range: -3.1752
Max Act: 3.0807. Min Act: -0.1700
Data Index: 4694735 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1752. Min Range: -3.1752
Max Act: 3.0807. Min Act: -0.1700
Data Index: 6971363 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1752. Min Range: -3.1752
Max Act: 3.0492. Min Act: -0.1700
Data Index: 5978032 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1752. Min Range: -3.1752
Max Act: 3.0650. Min Act: -0.1700
Data Index: 1529342 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1752. Min Range: -3.1752
Max Act: 3.0492. Min Act: -0.1700
Data Index: 6306554 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1752. Min Range: -3.1752
Max Act: 3.0334. Min Act: -0.1700
Data Index: 803495 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1752. Min Range: -3.1752
Max Act: 3.0334. Min Act: -0.1700
Data Index: 3104278 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1752. Min Range: -3.1752
Max Act: 3.0492. Min Act: -0.1700
Data Index: 266020 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1752. Min Range: -3.1752
Max Act: 3.0334. Min Act: -0.1700
Data Index: 5523649 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1752. Min Range: -3.1752
Max Act: 3.0176. Min Act: -0.1700
Data Index: 5217562 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1752. Min Range: -3.1752
Max Act: 3.0018. Min Act: -0.1700
Data Index: 7250290 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1752. Min Range: -3.1752
Max Act: 3.0018. Min Act: -0.1700
Data Index: 6326709 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1752. Min Range: -3.1752
Max Act: 2.9860. Min Act: -0.1700
Data Index: 8707164 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1752. Min Range: -3.1752
Max Act: 2.9860. Min Act: -0.1700
Data Index: 5501838 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1752. Min Range: -3.1752
Max Act: 2.9860. Min Act: -0.1700
Data Index: 4895942 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1752. Min Range: -3.1752
Max Act: 2.9544. Min Act: -0.1700
Data Index: 6667265 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #19