Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3591 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1414. Min Range: -7.1414
Max Act: 7.1414. Min Act: -0.1700
Data Index: 4771215 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1414. Min Range: -7.1414
Max Act: 7.1414. Min Act: -0.1700
Data Index: 318087 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1414. Min Range: -7.1414
Max Act: 7.1101. Min Act: -0.1700
Data Index: 489968 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1414. Min Range: -7.1414
Max Act: 7.1414. Min Act: -0.1700
Data Index: 1573980 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1414. Min Range: -7.1414
Max Act: 7.0789. Min Act: -0.1700
Data Index: 6568434 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1414. Min Range: -7.1414
Max Act: 7.0476. Min Act: -0.1700
Data Index: 5907501 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1414. Min Range: -7.1414
Max Act: 6.9539. Min Act: -0.1700
Data Index: 2468956 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1414. Min Range: -7.1414
Max Act: 6.9226. Min Act: -0.1700
Data Index: 1547481 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1414. Min Range: -7.1414
Max Act: 6.9226. Min Act: -0.1700
Data Index: 6943204 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1414. Min Range: -7.1414
Max Act: 6.9226. Min Act: -0.1700
Data Index: 8295709 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1414. Min Range: -7.1414
Max Act: 6.8914. Min Act: -0.1700
Data Index: 4748733 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1414. Min Range: -7.1414
Max Act: 6.8914. Min Act: -0.1700
Data Index: 6929455 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1414. Min Range: -7.1414
Max Act: 6.9226. Min Act: -0.1700
Data Index: 8829610 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1414. Min Range: -7.1414
Max Act: 6.9226. Min Act: -0.1700
Data Index: 1182583 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1414. Min Range: -7.1414
Max Act: 6.9226. Min Act: -0.1700
Data Index: 744206 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1414. Min Range: -7.1414
Max Act: 6.8914. Min Act: -0.1700
Data Index: 6114687 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1414. Min Range: -7.1414
Max Act: 6.8914. Min Act: -0.1700
Data Index: 2132219 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1414. Min Range: -7.1414
Max Act: 6.8914. Min Act: -0.1700
Data Index: 8800790 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1414. Min Range: -7.1414
Max Act: 6.8914. Min Act: -0.1700
Data Index: 844253 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1414. Min Range: -7.1414
Max Act: 6.8601. Min Act: -0.1700
Data Index: 1503423 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #19