Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4783 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6000. Min Range: -5.6000
Max Act: 5.6000. Min Act: -0.1700
Data Index: 5010415 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6000. Min Range: -5.6000
Max Act: 5.3500. Min Act: -0.1700
Data Index: 7649713 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6000. Min Range: -5.6000
Max Act: 5.2875. Min Act: -0.1700
Data Index: 2237241 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6000. Min Range: -5.6000
Max Act: 5.1937. Min Act: -0.1700
Data Index: 3571243 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6000. Min Range: -5.6000
Max Act: 5.2250. Min Act: -0.1700
Data Index: 1946122 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6000. Min Range: -5.6000
Max Act: 5.2250. Min Act: -0.1700
Data Index: 7906039 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6000. Min Range: -5.6000
Max Act: 5.1937. Min Act: -0.1700
Data Index: 1347074 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6000. Min Range: -5.6000
Max Act: 5.1000. Min Act: -0.1700
Data Index: 7577973 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6000. Min Range: -5.6000
Max Act: 5.0687. Min Act: -0.1700
Data Index: 3047373 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6000. Min Range: -5.6000
Max Act: 5.0687. Min Act: -0.1700
Data Index: 4478714 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6000. Min Range: -5.6000
Max Act: 5.0062. Min Act: -0.1700
Data Index: 5450308 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6000. Min Range: -5.6000
Max Act: 5.0062. Min Act: -0.1700
Data Index: 5117417 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6000. Min Range: -5.6000
Max Act: 5.0062. Min Act: -0.1700
Data Index: 1376565 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6000. Min Range: -5.6000
Max Act: 4.9437. Min Act: -0.1700
Data Index: 241035 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6000. Min Range: -5.6000
Max Act: 4.9437. Min Act: -0.1700
Data Index: 74404 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6000. Min Range: -5.6000
Max Act: 4.9437. Min Act: -0.1700
Data Index: 4922810 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6000. Min Range: -5.6000
Max Act: 4.9125. Min Act: -0.1700
Data Index: 644633 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6000. Min Range: -5.6000
Max Act: 4.9125. Min Act: -0.1700
Data Index: 4065548 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6000. Min Range: -5.6000
Max Act: 4.9125. Min Act: -0.1700
Data Index: 6199847 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6000. Min Range: -5.6000
Max Act: 4.9125. Min Act: -0.1700
Data Index: 1733856 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #19