Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5953 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9722. Min Range: -5.9722
Max Act: 5.9722. Min Act: -0.1700
Data Index: 223541 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9722. Min Range: -5.9722
Max Act: 5.8472. Min Act: -0.1700
Data Index: 4575330 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9722. Min Range: -5.9722
Max Act: 5.7534. Min Act: -0.1700
Data Index: 4938611 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9722. Min Range: -5.9722
Max Act: 5.7847. Min Act: -0.1700
Data Index: 8590099 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9722. Min Range: -5.9722
Max Act: 5.6909. Min Act: -0.1700
Data Index: 1001292 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9722. Min Range: -5.9722
Max Act: 5.6909. Min Act: -0.1700
Data Index: 6050317 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9722. Min Range: -5.9722
Max Act: 5.6597. Min Act: -0.1700
Data Index: 1838738 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9722. Min Range: -5.9722
Max Act: 5.6284. Min Act: -0.1700
Data Index: 5192948 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9722. Min Range: -5.9722
Max Act: 5.6597. Min Act: -0.1700
Data Index: 1813800 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9722. Min Range: -5.9722
Max Act: 5.6284. Min Act: -0.1700
Data Index: 7332407 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9722. Min Range: -5.9722
Max Act: 5.5659. Min Act: -0.1700
Data Index: 8737037 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9722. Min Range: -5.9722
Max Act: 5.5972. Min Act: -0.1700
Data Index: 7891171 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9722. Min Range: -5.9722
Max Act: 5.5972. Min Act: -0.1700
Data Index: 1571135 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9722. Min Range: -5.9722
Max Act: 5.5659. Min Act: -0.1700
Data Index: 3268178 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9722. Min Range: -5.9722
Max Act: 5.5659. Min Act: -0.1700
Data Index: 1775145 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9722. Min Range: -5.9722
Max Act: 5.5972. Min Act: -0.1700
Data Index: 5853035 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9722. Min Range: -5.9722
Max Act: 5.5347. Min Act: -0.1700
Data Index: 2650600 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9722. Min Range: -5.9722
Max Act: 5.5347. Min Act: -0.1700
Data Index: 1807618 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9722. Min Range: -5.9722
Max Act: 5.5347. Min Act: -0.1700
Data Index: 4129926 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9722. Min Range: -5.9722
Max Act: 5.5347. Min Act: -0.1700
Data Index: 1144233 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #19