Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 778 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6067. Min Range: -5.6067
Max Act: 5.6067. Min Act: -0.1700
Data Index: 7207173 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6067. Min Range: -5.6067
Max Act: 5.5442. Min Act: -0.1700
Data Index: 3558844 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6067. Min Range: -5.6067
Max Act: 5.5130. Min Act: -0.1700
Data Index: 5213663 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6067. Min Range: -5.6067
Max Act: 5.4505. Min Act: -0.1700
Data Index: 7129446 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6067. Min Range: -5.6067
Max Act: 5.4505. Min Act: -0.1700
Data Index: 2057666 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6067. Min Range: -5.6067
Max Act: 5.4505. Min Act: -0.1700
Data Index: 7323872 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6067. Min Range: -5.6067
Max Act: 5.4505. Min Act: -0.1700
Data Index: 4263101 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6067. Min Range: -5.6067
Max Act: 5.4505. Min Act: -0.1700
Data Index: 1120003 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6067. Min Range: -5.6067
Max Act: 5.4505. Min Act: -0.1700
Data Index: 1652668 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6067. Min Range: -5.6067
Max Act: 5.4192. Min Act: -0.1700
Data Index: 8210121 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6067. Min Range: -5.6067
Max Act: 5.4192. Min Act: -0.1700
Data Index: 3690509 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6067. Min Range: -5.6067
Max Act: 5.3880. Min Act: -0.1700
Data Index: 5490230 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6067. Min Range: -5.6067
Max Act: 5.3880. Min Act: -0.1700
Data Index: 760353 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6067. Min Range: -5.6067
Max Act: 5.3567. Min Act: -0.1700
Data Index: 4540306 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6067. Min Range: -5.6067
Max Act: 5.3880. Min Act: -0.1700
Data Index: 2966625 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6067. Min Range: -5.6067
Max Act: 5.3567. Min Act: -0.1700
Data Index: 6247807 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6067. Min Range: -5.6067
Max Act: 5.3567. Min Act: -0.1700
Data Index: 5826098 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6067. Min Range: -5.6067
Max Act: 5.3255. Min Act: -0.1700
Data Index: 4378589 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6067. Min Range: -5.6067
Max Act: 5.3255. Min Act: -0.1700
Data Index: 4857736 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6067. Min Range: -5.6067
Max Act: 5.3255. Min Act: -0.1700
Data Index: 7129447 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #19