Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2871 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5444. Min Range: -7.5444
Max Act: 7.5444. Min Act: -0.1700
Data Index: 1518295 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5444. Min Range: -7.5444
Max Act: 7.0132. Min Act: -0.1700
Data Index: 1897514 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5444. Min Range: -7.5444
Max Act: 7.0132. Min Act: -0.1700
Data Index: 7072726 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5444. Min Range: -7.5444
Max Act: 7.0132. Min Act: -0.1700
Data Index: 2872074 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5444. Min Range: -7.5444
Max Act: 7.0132. Min Act: -0.1700
Data Index: 5435148 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5444. Min Range: -7.5444
Max Act: 6.9819. Min Act: -0.1700
Data Index: 6973027 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5444. Min Range: -7.5444
Max Act: 6.9507. Min Act: -0.1700
Data Index: 2734313 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5444. Min Range: -7.5444
Max Act: 6.9819. Min Act: -0.1700
Data Index: 6560181 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5444. Min Range: -7.5444
Max Act: 6.9507. Min Act: -0.1700
Data Index: 8756445 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5444. Min Range: -7.5444
Max Act: 6.9819. Min Act: -0.1700
Data Index: 8323424 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5444. Min Range: -7.5444
Max Act: 6.9194. Min Act: -0.1700
Data Index: 6433320 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5444. Min Range: -7.5444
Max Act: 6.9194. Min Act: -0.1700
Data Index: 3403566 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5444. Min Range: -7.5444
Max Act: 6.8882. Min Act: -0.1700
Data Index: 7533275 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5444. Min Range: -7.5444
Max Act: 6.8882. Min Act: -0.1700
Data Index: 2129598 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5444. Min Range: -7.5444
Max Act: 6.8569. Min Act: -0.1700
Data Index: 5340383 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5444. Min Range: -7.5444
Max Act: 6.8569. Min Act: -0.1700
Data Index: 473927 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5444. Min Range: -7.5444
Max Act: 6.8882. Min Act: -0.1700
Data Index: 1101370 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5444. Min Range: -7.5444
Max Act: 6.8569. Min Act: -0.1700
Data Index: 5075829 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5444. Min Range: -7.5444
Max Act: 6.8882. Min Act: -0.1700
Data Index: 5010158 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5444. Min Range: -7.5444
Max Act: 6.8569. Min Act: -0.1700
Data Index: 5995408 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #19