Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3340 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0150. Min Range: -6.0150
Max Act: 6.0150. Min Act: -0.1700
Data Index: 4647321 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0150. Min Range: -6.0150
Max Act: 5.9212. Min Act: -0.1700
Data Index: 1562856 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0150. Min Range: -6.0150
Max Act: 5.9212. Min Act: -0.1700
Data Index: 1670123 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0150. Min Range: -6.0150
Max Act: 5.7650. Min Act: -0.1700
Data Index: 1886190 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0150. Min Range: -6.0150
Max Act: 5.7337. Min Act: -0.1700
Data Index: 8276031 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0150. Min Range: -6.0150
Max Act: 5.7337. Min Act: -0.1700
Data Index: 145990 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0150. Min Range: -6.0150
Max Act: 5.7025. Min Act: -0.1700
Data Index: 2977153 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0150. Min Range: -6.0150
Max Act: 5.6712. Min Act: -0.1700
Data Index: 6792760 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0150. Min Range: -6.0150
Max Act: 5.6087. Min Act: -0.1700
Data Index: 6245343 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0150. Min Range: -6.0150
Max Act: 5.6087. Min Act: -0.1700
Data Index: 4635784 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0150. Min Range: -6.0150
Max Act: 5.6400. Min Act: -0.1700
Data Index: 4183293 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0150. Min Range: -6.0150
Max Act: 5.5775. Min Act: -0.1700
Data Index: 1869527 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0150. Min Range: -6.0150
Max Act: 5.5775. Min Act: -0.1700
Data Index: 2224982 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0150. Min Range: -6.0150
Max Act: 5.5462. Min Act: -0.1700
Data Index: 7622100 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0150. Min Range: -6.0150
Max Act: 5.5462. Min Act: -0.1700
Data Index: 1996414 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0150. Min Range: -6.0150
Max Act: 5.5462. Min Act: -0.1700
Data Index: 2574090 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0150. Min Range: -6.0150
Max Act: 5.5150. Min Act: -0.1700
Data Index: 8706177 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0150. Min Range: -6.0150
Max Act: 5.4837. Min Act: -0.1700
Data Index: 5010223 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0150. Min Range: -6.0150
Max Act: 5.4837. Min Act: -0.1700
Data Index: 2436541 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0150. Min Range: -6.0150
Max Act: 5.5150. Min Act: -0.1700
Data Index: 3821081 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #19