Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3197 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5260. Min Range: -6.5260
Max Act: 6.5260. Min Act: -0.1700
Data Index: 302469 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5260. Min Range: -6.5260
Max Act: 6.4322. Min Act: -0.1700
Data Index: 4857881 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5260. Min Range: -6.5260
Max Act: 6.1197. Min Act: -0.1700
Data Index: 4857878 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5260. Min Range: -6.5260
Max Act: 6.1197. Min Act: -0.1700
Data Index: 2689854 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5260. Min Range: -6.5260
Max Act: 6.1197. Min Act: -0.1700
Data Index: 2288113 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5260. Min Range: -6.5260
Max Act: 6.0885. Min Act: -0.1700
Data Index: 2564994 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5260. Min Range: -6.5260
Max Act: 6.0260. Min Act: -0.1700
Data Index: 3836937 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5260. Min Range: -6.5260
Max Act: 6.0260. Min Act: -0.1700
Data Index: 6125871 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5260. Min Range: -6.5260
Max Act: 6.0572. Min Act: -0.1700
Data Index: 6150860 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5260. Min Range: -6.5260
Max Act: 6.0260. Min Act: -0.1700
Data Index: 7480475 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5260. Min Range: -6.5260
Max Act: 6.0260. Min Act: -0.1700
Data Index: 8188151 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5260. Min Range: -6.5260
Max Act: 6.0260. Min Act: -0.1700
Data Index: 7021621 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5260. Min Range: -6.5260
Max Act: 5.9947. Min Act: -0.1700
Data Index: 4857882 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5260. Min Range: -6.5260
Max Act: 5.9635. Min Act: -0.1700
Data Index: 1547426 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5260. Min Range: -6.5260
Max Act: 5.9635. Min Act: -0.1700
Data Index: 4164532 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5260. Min Range: -6.5260
Max Act: 5.9322. Min Act: -0.1700
Data Index: 4945690 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5260. Min Range: -6.5260
Max Act: 5.9322. Min Act: -0.1700
Data Index: 5827195 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5260. Min Range: -6.5260
Max Act: 5.9322. Min Act: -0.1700
Data Index: 4270745 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5260. Min Range: -6.5260
Max Act: 5.9635. Min Act: -0.1700
Data Index: 1461789 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5260. Min Range: -6.5260
Max Act: 5.9322. Min Act: -0.1700
Data Index: 1196411 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #19