Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 7 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6197. Min Range: -5.6197
Max Act: 5.6197. Min Act: -0.1700
Data Index: 8127357 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6197. Min Range: -5.6197
Max Act: 5.4947. Min Act: -0.1700
Data Index: 6262446 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6197. Min Range: -5.6197
Max Act: 5.4947. Min Act: -0.1700
Data Index: 1099211 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6197. Min Range: -5.6197
Max Act: 5.4322. Min Act: -0.1700
Data Index: 5416382 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6197. Min Range: -5.6197
Max Act: 5.4322. Min Act: -0.1700
Data Index: 4690155 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6197. Min Range: -5.6197
Max Act: 5.4322. Min Act: -0.1700
Data Index: 2926366 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6197. Min Range: -5.6197
Max Act: 5.4322. Min Act: -0.1700
Data Index: 2069669 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6197. Min Range: -5.6197
Max Act: 5.4010. Min Act: -0.1700
Data Index: 8275059 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6197. Min Range: -5.6197
Max Act: 5.4010. Min Act: -0.1700
Data Index: 5054962 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6197. Min Range: -5.6197
Max Act: 5.4322. Min Act: -0.1700
Data Index: 7929666 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6197. Min Range: -5.6197
Max Act: 5.4010. Min Act: -0.1700
Data Index: 3362525 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6197. Min Range: -5.6197
Max Act: 5.3697. Min Act: -0.1700
Data Index: 6269962 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6197. Min Range: -5.6197
Max Act: 5.3697. Min Act: -0.1700
Data Index: 7510339 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6197. Min Range: -5.6197
Max Act: 5.3697. Min Act: -0.1700
Data Index: 5871957 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6197. Min Range: -5.6197
Max Act: 5.3697. Min Act: -0.1700
Data Index: 8633905 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6197. Min Range: -5.6197
Max Act: 5.3697. Min Act: -0.1700
Data Index: 827885 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6197. Min Range: -5.6197
Max Act: 5.3385. Min Act: -0.1700
Data Index: 2633794 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6197. Min Range: -5.6197
Max Act: 5.3072. Min Act: -0.1700
Data Index: 7759083 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6197. Min Range: -5.6197
Max Act: 5.3385. Min Act: -0.1700
Data Index: 1959780 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6197. Min Range: -5.6197
Max Act: 5.3385. Min Act: -0.1700
Data Index: 17627 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #19