Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1238 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5167. Min Range: -3.5167
Max Act: 3.5167. Min Act: -0.1700
Data Index: 1995311 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5167. Min Range: -3.5167
Max Act: 3.4071. Min Act: -0.1700
Data Index: 8786793 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5167. Min Range: -3.5167
Max Act: 3.3757. Min Act: -0.1700
Data Index: 8324875 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5167. Min Range: -3.5167
Max Act: 3.3600. Min Act: -0.1700
Data Index: 4720130 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5167. Min Range: -3.5167
Max Act: 3.3757. Min Act: -0.1700
Data Index: 8786790 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5167. Min Range: -3.5167
Max Act: 3.3757. Min Act: -0.1700
Data Index: 6080491 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5167. Min Range: -3.5167
Max Act: 3.3129. Min Act: -0.1700
Data Index: 3975239 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5167. Min Range: -3.5167
Max Act: 3.2815. Min Act: -0.1700
Data Index: 5282586 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5167. Min Range: -3.5167
Max Act: 3.2658. Min Act: -0.1700
Data Index: 5677039 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5167. Min Range: -3.5167
Max Act: 3.2815. Min Act: -0.1700
Data Index: 7119377 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5167. Min Range: -3.5167
Max Act: 3.2501. Min Act: -0.1700
Data Index: 4966135 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5167. Min Range: -3.5167
Max Act: 3.2658. Min Act: -0.1700
Data Index: 4720131 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5167. Min Range: -3.5167
Max Act: 3.2501. Min Act: -0.1700
Data Index: 2528241 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5167. Min Range: -3.5167
Max Act: 3.2344. Min Act: -0.1700
Data Index: 7176472 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5167. Min Range: -3.5167
Max Act: 3.2344. Min Act: -0.1700
Data Index: 5743463 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5167. Min Range: -3.5167
Max Act: 3.2501. Min Act: -0.1700
Data Index: 8294141 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5167. Min Range: -3.5167
Max Act: 3.2344. Min Act: -0.1700
Data Index: 1861943 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5167. Min Range: -3.5167
Max Act: 3.2344. Min Act: -0.1700
Data Index: 7301789 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5167. Min Range: -3.5167
Max Act: 3.2030. Min Act: -0.1700
Data Index: 2499469 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5167. Min Range: -3.5167
Max Act: 3.1873. Min Act: -0.1700
Data Index: 977826 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #19