Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3785 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1519. Min Range: -7.1519
Max Act: 7.1519. Min Act: -0.1700
Data Index: 4574362 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1519. Min Range: -7.1519
Max Act: 6.8082. Min Act: -0.1700
Data Index: 5825287 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1519. Min Range: -7.1519
Max Act: 6.6519. Min Act: -0.1700
Data Index: 7687521 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1519. Min Range: -7.1519
Max Act: 6.5894. Min Act: -0.1700
Data Index: 5285560 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1519. Min Range: -7.1519
Max Act: 6.5582. Min Act: -0.1700
Data Index: 2232651 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1519. Min Range: -7.1519
Max Act: 6.5582. Min Act: -0.1700
Data Index: 7977352 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1519. Min Range: -7.1519
Max Act: 6.5582. Min Act: -0.1700
Data Index: 7784763 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1519. Min Range: -7.1519
Max Act: 6.5269. Min Act: -0.1700
Data Index: 8681478 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1519. Min Range: -7.1519
Max Act: 6.4957. Min Act: -0.1700
Data Index: 1786275 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1519. Min Range: -7.1519
Max Act: 6.5269. Min Act: -0.1700
Data Index: 5904724 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1519. Min Range: -7.1519
Max Act: 6.4644. Min Act: -0.1700
Data Index: 3729597 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1519. Min Range: -7.1519
Max Act: 6.4644. Min Act: -0.1700
Data Index: 4709554 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1519. Min Range: -7.1519
Max Act: 6.4332. Min Act: -0.1700
Data Index: 6106918 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1519. Min Range: -7.1519
Max Act: 6.4644. Min Act: -0.1700
Data Index: 2629715 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1519. Min Range: -7.1519
Max Act: 6.4644. Min Act: -0.1700
Data Index: 5501993 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1519. Min Range: -7.1519
Max Act: 6.4332. Min Act: -0.1700
Data Index: 3535308 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1519. Min Range: -7.1519
Max Act: 6.4332. Min Act: -0.1700
Data Index: 7181568 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1519. Min Range: -7.1519
Max Act: 6.4332. Min Act: -0.1700
Data Index: 7878493 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1519. Min Range: -7.1519
Max Act: 6.4644. Min Act: -0.1700
Data Index: 8812375 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1519. Min Range: -7.1519
Max Act: 6.4332. Min Act: -0.1700
Data Index: 7621567 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #19