Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1543 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8308. Min Range: -7.8308
Max Act: 7.8308. Min Act: -0.1700
Data Index: 4232443 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8308. Min Range: -7.8308
Max Act: 7.8308. Min Act: -0.1700
Data Index: 8306473 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8308. Min Range: -7.8308
Max Act: 7.8308. Min Act: -0.1700
Data Index: 1721007 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8308. Min Range: -7.8308
Max Act: 7.7058. Min Act: -0.1700
Data Index: 3468754 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8308. Min Range: -7.8308
Max Act: 7.7058. Min Act: -0.1700
Data Index: 6252808 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8308. Min Range: -7.8308
Max Act: 7.6745. Min Act: -0.1700
Data Index: 8306474 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8308. Min Range: -7.8308
Max Act: 7.6120. Min Act: -0.1700
Data Index: 4125364 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8308. Min Range: -7.8308
Max Act: 7.6120. Min Act: -0.1700
Data Index: 3842302 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8308. Min Range: -7.8308
Max Act: 7.6120. Min Act: -0.1700
Data Index: 6388171 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8308. Min Range: -7.8308
Max Act: 7.5495. Min Act: -0.1700
Data Index: 5142857 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8308. Min Range: -7.8308
Max Act: 7.5495. Min Act: -0.1700
Data Index: 1709119 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8308. Min Range: -7.8308
Max Act: 7.5495. Min Act: -0.1700
Data Index: 4573578 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8308. Min Range: -7.8308
Max Act: 7.5183. Min Act: -0.1700
Data Index: 248899 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8308. Min Range: -7.8308
Max Act: 7.5183. Min Act: -0.1700
Data Index: 7049047 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8308. Min Range: -7.8308
Max Act: 7.5183. Min Act: -0.1700
Data Index: 1455470 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8308. Min Range: -7.8308
Max Act: 7.5183. Min Act: -0.1700
Data Index: 2338016 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8308. Min Range: -7.8308
Max Act: 7.4870. Min Act: -0.1700
Data Index: 1795320 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8308. Min Range: -7.8308
Max Act: 7.4870. Min Act: -0.1700
Data Index: 4355642 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8308. Min Range: -7.8308
Max Act: 7.5183. Min Act: -0.1700
Data Index: 6226031 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8308. Min Range: -7.8308
Max Act: 7.4558. Min Act: -0.1700
Data Index: 5196168 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #19