Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2640 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1801. Min Range: -7.1801
Max Act: 7.1801. Min Act: -0.1700
Data Index: 454805 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1801. Min Range: -7.1801
Max Act: 6.8363. Min Act: -0.1700
Data Index: 3811336 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1801. Min Range: -7.1801
Max Act: 6.8051. Min Act: -0.1700
Data Index: 8562127 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1801. Min Range: -7.1801
Max Act: 6.8051. Min Act: -0.1700
Data Index: 8251340 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1801. Min Range: -7.1801
Max Act: 6.8051. Min Act: -0.1700
Data Index: 5152373 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1801. Min Range: -7.1801
Max Act: 6.8051. Min Act: -0.1700
Data Index: 8638098 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1801. Min Range: -7.1801
Max Act: 6.7426. Min Act: -0.1700
Data Index: 5670206 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1801. Min Range: -7.1801
Max Act: 6.7738. Min Act: -0.1700
Data Index: 8265423 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1801. Min Range: -7.1801
Max Act: 6.7426. Min Act: -0.1700
Data Index: 5071972 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1801. Min Range: -7.1801
Max Act: 6.7113. Min Act: -0.1700
Data Index: 8562128 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1801. Min Range: -7.1801
Max Act: 6.7426. Min Act: -0.1700
Data Index: 7814434 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1801. Min Range: -7.1801
Max Act: 6.7113. Min Act: -0.1700
Data Index: 356411 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1801. Min Range: -7.1801
Max Act: 6.7113. Min Act: -0.1700
Data Index: 2079056 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1801. Min Range: -7.1801
Max Act: 6.7426. Min Act: -0.1700
Data Index: 6716729 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1801. Min Range: -7.1801
Max Act: 6.7113. Min Act: -0.1700
Data Index: 5398141 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1801. Min Range: -7.1801
Max Act: 6.7113. Min Act: -0.1700
Data Index: 7231353 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1801. Min Range: -7.1801
Max Act: 6.6801. Min Act: -0.1700
Data Index: 4497317 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1801. Min Range: -7.1801
Max Act: 6.7113. Min Act: -0.1700
Data Index: 4555016 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1801. Min Range: -7.1801
Max Act: 6.7113. Min Act: -0.1700
Data Index: 6389404 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1801. Min Range: -7.1801
Max Act: 6.7113. Min Act: -0.1700
Data Index: 5245994 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #19