Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4826 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7190. Min Range: -7.7190
Max Act: 7.7190. Min Act: -0.1700
Data Index: 861740 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7190. Min Range: -7.7190
Max Act: 7.2815. Min Act: -0.1700
Data Index: 5759370 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7190. Min Range: -7.7190
Max Act: 7.1878. Min Act: -0.1700
Data Index: 6230137 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7190. Min Range: -7.7190
Max Act: 7.1565. Min Act: -0.1700
Data Index: 4811968 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7190. Min Range: -7.7190
Max Act: 7.1878. Min Act: -0.1700
Data Index: 2282201 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7190. Min Range: -7.7190
Max Act: 7.2190. Min Act: -0.1700
Data Index: 1700098 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7190. Min Range: -7.7190
Max Act: 7.0315. Min Act: -0.1700
Data Index: 1700096 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7190. Min Range: -7.7190
Max Act: 6.9378. Min Act: -0.1700
Data Index: 209037 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7190. Min Range: -7.7190
Max Act: 6.9378. Min Act: -0.1700
Data Index: 2856219 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7190. Min Range: -7.7190
Max Act: 6.9378. Min Act: -0.1700
Data Index: 330843 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7190. Min Range: -7.7190
Max Act: 6.9378. Min Act: -0.1700
Data Index: 679639 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7190. Min Range: -7.7190
Max Act: 6.9065. Min Act: -0.1700
Data Index: 2856217 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7190. Min Range: -7.7190
Max Act: 6.9065. Min Act: -0.1700
Data Index: 6800105 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7190. Min Range: -7.7190
Max Act: 6.9065. Min Act: -0.1700
Data Index: 2091044 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7190. Min Range: -7.7190
Max Act: 6.9065. Min Act: -0.1700
Data Index: 1700086 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7190. Min Range: -7.7190
Max Act: 6.9378. Min Act: -0.1700
Data Index: 861741 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7190. Min Range: -7.7190
Max Act: 6.9065. Min Act: -0.1700
Data Index: 271377 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7190. Min Range: -7.7190
Max Act: 6.9065. Min Act: -0.1700
Data Index: 813455 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7190. Min Range: -7.7190
Max Act: 6.8753. Min Act: -0.1700
Data Index: 6800107 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7190. Min Range: -7.7190
Max Act: 6.8753. Min Act: -0.1700
Data Index: 749587 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #19