Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5713 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3281. Min Range: -6.3281
Max Act: 6.3281. Min Act: -0.1700
Data Index: 4493693 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3281. Min Range: -6.3281
Max Act: 5.8906. Min Act: -0.1700
Data Index: 4778850 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3281. Min Range: -6.3281
Max Act: 5.8906. Min Act: -0.1700
Data Index: 7136200 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3281. Min Range: -6.3281
Max Act: 5.8593. Min Act: -0.1700
Data Index: 4906297 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3281. Min Range: -6.3281
Max Act: 5.7968. Min Act: -0.1700
Data Index: 5884885 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3281. Min Range: -6.3281
Max Act: 5.7656. Min Act: -0.1700
Data Index: 6609266 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3281. Min Range: -6.3281
Max Act: 5.7656. Min Act: -0.1700
Data Index: 5696025 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3281. Min Range: -6.3281
Max Act: 5.6718. Min Act: -0.1700
Data Index: 2585098 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3281. Min Range: -6.3281
Max Act: 5.6718. Min Act: -0.1700
Data Index: 2332452 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3281. Min Range: -6.3281
Max Act: 5.6718. Min Act: -0.1700
Data Index: 4830627 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3281. Min Range: -6.3281
Max Act: 5.6406. Min Act: -0.1700
Data Index: 3764606 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3281. Min Range: -6.3281
Max Act: 5.6406. Min Act: -0.1700
Data Index: 1721952 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3281. Min Range: -6.3281
Max Act: 5.6093. Min Act: -0.1700
Data Index: 1374650 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3281. Min Range: -6.3281
Max Act: 5.6093. Min Act: -0.1700
Data Index: 405988 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3281. Min Range: -6.3281
Max Act: 5.6406. Min Act: -0.1700
Data Index: 2573921 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3281. Min Range: -6.3281
Max Act: 5.6093. Min Act: -0.1700
Data Index: 4126160 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3281. Min Range: -6.3281
Max Act: 5.5781. Min Act: -0.1700
Data Index: 141038 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3281. Min Range: -6.3281
Max Act: 5.5781. Min Act: -0.1700
Data Index: 5275306 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3281. Min Range: -6.3281
Max Act: 5.5781. Min Act: -0.1700
Data Index: 7873176 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3281. Min Range: -6.3281
Max Act: 5.5468. Min Act: -0.1700
Data Index: 7368105 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #19