Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2652 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2461. Min Range: -8.2461
Max Act: 8.2461. Min Act: -0.1700
Data Index: 3862844 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2461. Min Range: -8.2461
Max Act: 8.1836. Min Act: -0.1700
Data Index: 1500720 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2461. Min Range: -8.2461
Max Act: 7.9336. Min Act: -0.1700
Data Index: 1128698 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2461. Min Range: -8.2461
Max Act: 7.9336. Min Act: -0.1700
Data Index: 6233747 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2461. Min Range: -8.2461
Max Act: 7.8086. Min Act: -0.1700
Data Index: 3149542 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2461. Min Range: -8.2461
Max Act: 7.8086. Min Act: -0.1700
Data Index: 21325 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2461. Min Range: -8.2461
Max Act: 7.7461. Min Act: -0.1700
Data Index: 1123068 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2461. Min Range: -8.2461
Max Act: 7.7461. Min Act: -0.1700
Data Index: 5643184 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2461. Min Range: -8.2461
Max Act: 7.7148. Min Act: -0.1700
Data Index: 1049226 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2461. Min Range: -8.2461
Max Act: 7.7148. Min Act: -0.1700
Data Index: 276214 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2461. Min Range: -8.2461
Max Act: 7.7148. Min Act: -0.1700
Data Index: 4108645 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2461. Min Range: -8.2461
Max Act: 7.6836. Min Act: -0.1700
Data Index: 4968142 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2461. Min Range: -8.2461
Max Act: 7.6523. Min Act: -0.1700
Data Index: 3503457 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2461. Min Range: -8.2461
Max Act: 7.6836. Min Act: -0.1700
Data Index: 5865112 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2461. Min Range: -8.2461
Max Act: 7.6523. Min Act: -0.1700
Data Index: 7944434 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2461. Min Range: -8.2461
Max Act: 7.6523. Min Act: -0.1700
Data Index: 1948709 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2461. Min Range: -8.2461
Max Act: 7.6523. Min Act: -0.1700
Data Index: 6957076 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2461. Min Range: -8.2461
Max Act: 7.6211. Min Act: -0.1700
Data Index: 1322877 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2461. Min Range: -8.2461
Max Act: 7.6523. Min Act: -0.1700
Data Index: 511958 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2461. Min Range: -8.2461
Max Act: 7.6211. Min Act: -0.1700
Data Index: 3053957 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #19