Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5831 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8260. Min Range: -8.8260
Max Act: 8.8260. Min Act: -0.1700
Data Index: 2195895 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8260. Min Range: -8.8260
Max Act: 8.5135. Min Act: -0.1700
Data Index: 5380813 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8260. Min Range: -8.8260
Max Act: 8.5135. Min Act: -0.1700
Data Index: 3251850 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8260. Min Range: -8.8260
Max Act: 8.3260. Min Act: -0.1700
Data Index: 1895832 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8260. Min Range: -8.8260
Max Act: 8.2323. Min Act: -0.1700
Data Index: 8108419 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8260. Min Range: -8.8260
Max Act: 8.1385. Min Act: -0.1700
Data Index: 2585447 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8260. Min Range: -8.8260
Max Act: 8.1385. Min Act: -0.1700
Data Index: 7324331 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8260. Min Range: -8.8260
Max Act: 8.2010. Min Act: -0.1700
Data Index: 3320497 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8260. Min Range: -8.8260
Max Act: 7.9823. Min Act: -0.1700
Data Index: 2850647 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8260. Min Range: -8.8260
Max Act: 7.8885. Min Act: -0.1700
Data Index: 2919982 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8260. Min Range: -8.8260
Max Act: 7.8573. Min Act: -0.1700
Data Index: 3741716 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8260. Min Range: -8.8260
Max Act: 7.8260. Min Act: -0.1700
Data Index: 5137293 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8260. Min Range: -8.8260
Max Act: 7.8260. Min Act: -0.1700
Data Index: 129154 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8260. Min Range: -8.8260
Max Act: 7.7948. Min Act: -0.1700
Data Index: 2823244 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8260. Min Range: -8.8260
Max Act: 7.7635. Min Act: -0.1700
Data Index: 4626901 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8260. Min Range: -8.8260
Max Act: 7.7010. Min Act: -0.1700
Data Index: 6080594 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8260. Min Range: -8.8260
Max Act: 7.7635. Min Act: -0.1700
Data Index: 4564714 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8260. Min Range: -8.8260
Max Act: 7.7010. Min Act: -0.1700
Data Index: 3659066 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8260. Min Range: -8.8260
Max Act: 7.6698. Min Act: -0.1700
Data Index: 521450 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8260. Min Range: -8.8260
Max Act: 7.6698. Min Act: -0.1700
Data Index: 1859057 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #19