Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1727 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6213. Min Range: -8.6213
Max Act: 8.6213. Min Act: -0.1700
Data Index: 4824994 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6213. Min Range: -8.6213
Max Act: 8.4338. Min Act: -0.1700
Data Index: 4824996 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6213. Min Range: -8.6213
Max Act: 8.3088. Min Act: -0.1700
Data Index: 5678758 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6213. Min Range: -8.6213
Max Act: 8.2463. Min Act: -0.1700
Data Index: 4896508 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6213. Min Range: -8.6213
Max Act: 8.1838. Min Act: -0.1700
Data Index: 324721 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6213. Min Range: -8.6213
Max Act: 8.1838. Min Act: -0.1700
Data Index: 4824998 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6213. Min Range: -8.6213
Max Act: 8.2463. Min Act: -0.1700
Data Index: 3452093 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6213. Min Range: -8.6213
Max Act: 7.9338. Min Act: -0.1700
Data Index: 2706091 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6213. Min Range: -8.6213
Max Act: 7.9651. Min Act: -0.1700
Data Index: 535800 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6213. Min Range: -8.6213
Max Act: 7.9026. Min Act: -0.1700
Data Index: 5958635 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6213. Min Range: -8.6213
Max Act: 7.8401. Min Act: -0.1700
Data Index: 89092 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6213. Min Range: -8.6213
Max Act: 7.8088. Min Act: -0.1700
Data Index: 8174919 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6213. Min Range: -8.6213
Max Act: 7.7776. Min Act: -0.1700
Data Index: 8386 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6213. Min Range: -8.6213
Max Act: 7.7776. Min Act: -0.1700
Data Index: 1659993 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6213. Min Range: -8.6213
Max Act: 7.7776. Min Act: -0.1700
Data Index: 1995887 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6213. Min Range: -8.6213
Max Act: 7.7776. Min Act: -0.1700
Data Index: 1966022 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6213. Min Range: -8.6213
Max Act: 7.7776. Min Act: -0.1700
Data Index: 3766669 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6213. Min Range: -8.6213
Max Act: 7.6838. Min Act: -0.1700
Data Index: 1265898 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6213. Min Range: -8.6213
Max Act: 7.6526. Min Act: -0.1700
Data Index: 2653631 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6213. Min Range: -8.6213
Max Act: 7.6526. Min Act: -0.1700
Data Index: 2889109 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #19