Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2251 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.1126. Min Range: -7.1126
Max Act: 7.1126. Min Act: -0.1700
Data Index: 2651894 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1126. Min Range: -7.1126
Max Act: 7.0188. Min Act: -0.1700
Data Index: 6425454 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1126. Min Range: -7.1126
Max Act: 6.9251. Min Act: -0.1700
Data Index: 780743 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1126. Min Range: -7.1126
Max Act: 6.8938. Min Act: -0.1700
Data Index: 5411008 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1126. Min Range: -7.1126
Max Act: 6.8313. Min Act: -0.1700
Data Index: 6999770 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1126. Min Range: -7.1126
Max Act: 6.7063. Min Act: -0.1700
Data Index: 951860 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1126. Min Range: -7.1126
Max Act: 6.6126. Min Act: -0.1700
Data Index: 7214562 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1126. Min Range: -7.1126
Max Act: 6.6126. Min Act: -0.1700
Data Index: 4071621 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1126. Min Range: -7.1126
Max Act: 6.5813. Min Act: -0.1700
Data Index: 6399299 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1126. Min Range: -7.1126
Max Act: 6.6126. Min Act: -0.1700
Data Index: 3210751 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1126. Min Range: -7.1126
Max Act: 6.6126. Min Act: -0.1700
Data Index: 7007759 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1126. Min Range: -7.1126
Max Act: 6.6126. Min Act: -0.1700
Data Index: 7376988 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1126. Min Range: -7.1126
Max Act: 6.6126. Min Act: -0.1700
Data Index: 5088612 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1126. Min Range: -7.1126
Max Act: 6.5501. Min Act: -0.1700
Data Index: 7953027 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1126. Min Range: -7.1126
Max Act: 6.5813. Min Act: -0.1700
Data Index: 314585 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1126. Min Range: -7.1126
Max Act: 6.6126. Min Act: -0.1700
Data Index: 5856279 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1126. Min Range: -7.1126
Max Act: 6.5501. Min Act: -0.1700
Data Index: 522385 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1126. Min Range: -7.1126
Max Act: 6.5501. Min Act: -0.1700
Data Index: 7677204 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1126. Min Range: -7.1126
Max Act: 6.5501. Min Act: -0.1700
Data Index: 7916693 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1126. Min Range: -7.1126
Max Act: 6.5813. Min Act: -0.1700
Data Index: 2671048 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #19