Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2789 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1385. Min Range: -8.1385
Max Act: 8.1385. Min Act: -0.1700
Data Index: 5704426 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1385. Min Range: -8.1385
Max Act: 8.0760. Min Act: -0.1700
Data Index: 4477517 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1385. Min Range: -8.1385
Max Act: 8.0135. Min Act: -0.1700
Data Index: 6437532 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1385. Min Range: -8.1385
Max Act: 8.0135. Min Act: -0.1700
Data Index: 218161 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1385. Min Range: -8.1385
Max Act: 7.9510. Min Act: -0.1700
Data Index: 1369565 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1385. Min Range: -8.1385
Max Act: 7.9510. Min Act: -0.1700
Data Index: 4431809 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1385. Min Range: -8.1385
Max Act: 7.8885. Min Act: -0.1700
Data Index: 5936080 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1385. Min Range: -8.1385
Max Act: 7.8260. Min Act: -0.1700
Data Index: 1963265 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1385. Min Range: -8.1385
Max Act: 7.8260. Min Act: -0.1700
Data Index: 4647770 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1385. Min Range: -8.1385
Max Act: 7.8260. Min Act: -0.1700
Data Index: 5500152 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1385. Min Range: -8.1385
Max Act: 7.8260. Min Act: -0.1700
Data Index: 8782490 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1385. Min Range: -8.1385
Max Act: 7.8260. Min Act: -0.1700
Data Index: 3681896 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1385. Min Range: -8.1385
Max Act: 7.8260. Min Act: -0.1700
Data Index: 7022720 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1385. Min Range: -8.1385
Max Act: 7.8260. Min Act: -0.1700
Data Index: 6488029 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1385. Min Range: -8.1385
Max Act: 7.7635. Min Act: -0.1700
Data Index: 5583880 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1385. Min Range: -8.1385
Max Act: 7.8260. Min Act: -0.1700
Data Index: 2047704 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1385. Min Range: -8.1385
Max Act: 7.7323. Min Act: -0.1700
Data Index: 5605367 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1385. Min Range: -8.1385
Max Act: 7.7323. Min Act: -0.1700
Data Index: 5292707 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1385. Min Range: -8.1385
Max Act: 7.7323. Min Act: -0.1700
Data Index: 6004118 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1385. Min Range: -8.1385
Max Act: 7.7323. Min Act: -0.1700
Data Index: 60166 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #19