Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4682 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6150. Min Range: -6.6150
Max Act: 6.6150. Min Act: -0.1700
Data Index: 4763050 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6150. Min Range: -6.6150
Max Act: 6.4900. Min Act: -0.1700
Data Index: 4763056 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6150. Min Range: -6.6150
Max Act: 6.3025. Min Act: -0.1700
Data Index: 4763047 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6150. Min Range: -6.6150
Max Act: 6.2087. Min Act: -0.1700
Data Index: 3634472 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6150. Min Range: -6.6150
Max Act: 6.2087. Min Act: -0.1700
Data Index: 5087110 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6150. Min Range: -6.6150
Max Act: 6.1150. Min Act: -0.1700
Data Index: 6157338 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6150. Min Range: -6.6150
Max Act: 5.9587. Min Act: -0.1700
Data Index: 4763048 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6150. Min Range: -6.6150
Max Act: 5.9587. Min Act: -0.1700
Data Index: 1557328 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6150. Min Range: -6.6150
Max Act: 5.9275. Min Act: -0.1700
Data Index: 4763055 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6150. Min Range: -6.6150
Max Act: 5.8962. Min Act: -0.1700
Data Index: 6736041 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6150. Min Range: -6.6150
Max Act: 5.8650. Min Act: -0.1700
Data Index: 2902931 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6150. Min Range: -6.6150
Max Act: 5.8650. Min Act: -0.1700
Data Index: 2391067 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6150. Min Range: -6.6150
Max Act: 5.8650. Min Act: -0.1700
Data Index: 3345862 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6150. Min Range: -6.6150
Max Act: 5.8337. Min Act: -0.1700
Data Index: 5289077 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6150. Min Range: -6.6150
Max Act: 5.8025. Min Act: -0.1700
Data Index: 1898317 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6150. Min Range: -6.6150
Max Act: 5.8025. Min Act: -0.1700
Data Index: 5458070 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6150. Min Range: -6.6150
Max Act: 5.8025. Min Act: -0.1700
Data Index: 1967838 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6150. Min Range: -6.6150
Max Act: 5.7712. Min Act: -0.1700
Data Index: 858793 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6150. Min Range: -6.6150
Max Act: 5.7712. Min Act: -0.1700
Data Index: 2998084 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6150. Min Range: -6.6150
Max Act: 5.7712. Min Act: -0.1700
Data Index: 4608730 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #19