Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1409 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5466. Min Range: -9.5466
Max Act: 9.5466. Min Act: -0.1700
Data Index: 7856524 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5466. Min Range: -9.5466
Max Act: 8.9216. Min Act: -0.1700
Data Index: 5392007 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5466. Min Range: -9.5466
Max Act: 8.9841. Min Act: -0.1700
Data Index: 6719141 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5466. Min Range: -9.5466
Max Act: 8.8591. Min Act: -0.1700
Data Index: 6374336 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5466. Min Range: -9.5466
Max Act: 8.7966. Min Act: -0.1700
Data Index: 6180040 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5466. Min Range: -9.5466
Max Act: 8.7341. Min Act: -0.1700
Data Index: 8197701 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5466. Min Range: -9.5466
Max Act: 8.6716. Min Act: -0.1700
Data Index: 8491651 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5466. Min Range: -9.5466
Max Act: 8.7341. Min Act: -0.1700
Data Index: 6374337 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5466. Min Range: -9.5466
Max Act: 8.6716. Min Act: -0.1700
Data Index: 6180041 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5466. Min Range: -9.5466
Max Act: 8.6716. Min Act: -0.1700
Data Index: 1614598 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5466. Min Range: -9.5466
Max Act: 8.6716. Min Act: -0.1700
Data Index: 5994282 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5466. Min Range: -9.5466
Max Act: 8.6091. Min Act: -0.1700
Data Index: 5678486 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5466. Min Range: -9.5466
Max Act: 8.6091. Min Act: -0.1700
Data Index: 2916753 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5466. Min Range: -9.5466
Max Act: 8.5466. Min Act: -0.1700
Data Index: 5146699 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5466. Min Range: -9.5466
Max Act: 8.5466. Min Act: -0.1700
Data Index: 7072454 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5466. Min Range: -9.5466
Max Act: 8.5466. Min Act: -0.1700
Data Index: 607995 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5466. Min Range: -9.5466
Max Act: 8.5466. Min Act: -0.1700
Data Index: 1707283 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5466. Min Range: -9.5466
Max Act: 8.4841. Min Act: -0.1700
Data Index: 423915 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5466. Min Range: -9.5466
Max Act: 8.3279. Min Act: -0.1700
Data Index: 8290175 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5466. Min Range: -9.5466
Max Act: 8.3591. Min Act: -0.1700
Data Index: 7533057 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #19