Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5779 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7405. Min Range: -5.7405
Max Act: 5.7405. Min Act: -0.1700
Data Index: 4277054 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7405. Min Range: -5.7405
Max Act: 5.5530. Min Act: -0.1700
Data Index: 3052310 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7405. Min Range: -5.7405
Max Act: 5.5217. Min Act: -0.1700
Data Index: 8266050 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7405. Min Range: -5.7405
Max Act: 5.5217. Min Act: -0.1700
Data Index: 3266366 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7405. Min Range: -5.7405
Max Act: 5.4905. Min Act: -0.1700
Data Index: 3306017 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7405. Min Range: -5.7405
Max Act: 5.4280. Min Act: -0.1700
Data Index: 5141835 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7405. Min Range: -5.7405
Max Act: 5.3655. Min Act: -0.1700
Data Index: 5445116 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7405. Min Range: -5.7405
Max Act: 5.3967. Min Act: -0.1700
Data Index: 4336611 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7405. Min Range: -5.7405
Max Act: 5.3655. Min Act: -0.1700
Data Index: 4149771 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7405. Min Range: -5.7405
Max Act: 5.3342. Min Act: -0.1700
Data Index: 2738413 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7405. Min Range: -5.7405
Max Act: 5.3030. Min Act: -0.1700
Data Index: 4653463 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7405. Min Range: -5.7405
Max Act: 5.3030. Min Act: -0.1700
Data Index: 301730 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7405. Min Range: -5.7405
Max Act: 5.2717. Min Act: -0.1700
Data Index: 1406105 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7405. Min Range: -5.7405
Max Act: 5.2717. Min Act: -0.1700
Data Index: 3618668 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7405. Min Range: -5.7405
Max Act: 5.2717. Min Act: -0.1700
Data Index: 1531542 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7405. Min Range: -5.7405
Max Act: 5.2717. Min Act: -0.1700
Data Index: 2713447 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7405. Min Range: -5.7405
Max Act: 5.3030. Min Act: -0.1700
Data Index: 3898382 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7405. Min Range: -5.7405
Max Act: 5.2717. Min Act: -0.1700
Data Index: 5241411 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7405. Min Range: -5.7405
Max Act: 5.2405. Min Act: -0.1700
Data Index: 3200380 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7405. Min Range: -5.7405
Max Act: 5.2405. Min Act: -0.1700
Data Index: 5720672 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #19