Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5187 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4342. Min Range: -3.4342
Max Act: 3.4342. Min Act: -0.1700
Data Index: 5830613 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4342. Min Range: -3.4342
Max Act: 3.4342. Min Act: -0.1700
Data Index: 336664 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4342. Min Range: -3.4342
Max Act: 3.4185. Min Act: -0.1700
Data Index: 6862851 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4342. Min Range: -3.4342
Max Act: 3.4029. Min Act: -0.1700
Data Index: 7819600 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4342. Min Range: -3.4342
Max Act: 3.3872. Min Act: -0.1700
Data Index: 4679989 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4342. Min Range: -3.4342
Max Act: 3.3558. Min Act: -0.1700
Data Index: 4853865 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4342. Min Range: -3.4342
Max Act: 3.3401. Min Act: -0.1700
Data Index: 5187260 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4342. Min Range: -3.4342
Max Act: 3.3401. Min Act: -0.1700
Data Index: 3387949 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4342. Min Range: -3.4342
Max Act: 3.3401. Min Act: -0.1700
Data Index: 1035461 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4342. Min Range: -3.4342
Max Act: 3.3401. Min Act: -0.1700
Data Index: 7669066 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4342. Min Range: -3.4342
Max Act: 3.3244. Min Act: -0.1700
Data Index: 44583 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4342. Min Range: -3.4342
Max Act: 3.3401. Min Act: -0.1700
Data Index: 7206156 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4342. Min Range: -3.4342
Max Act: 3.3244. Min Act: -0.1700
Data Index: 36180 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4342. Min Range: -3.4342
Max Act: 3.3244. Min Act: -0.1700
Data Index: 3986820 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4342. Min Range: -3.4342
Max Act: 3.3244. Min Act: -0.1700
Data Index: 7855796 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4342. Min Range: -3.4342
Max Act: 3.3087. Min Act: -0.1700
Data Index: 7225240 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4342. Min Range: -3.4342
Max Act: 3.3087. Min Act: -0.1700
Data Index: 7936520 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4342. Min Range: -3.4342
Max Act: 3.2930. Min Act: -0.1700
Data Index: 3628322 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4342. Min Range: -3.4342
Max Act: 3.2773. Min Act: -0.1700
Data Index: 3216963 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4342. Min Range: -3.4342
Max Act: 3.2773. Min Act: -0.1700
Data Index: 1369871 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #19