Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5046 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4409. Min Range: -4.4409
Max Act: 4.4409. Min Act: -0.1700
Data Index: 6059132 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4409. Min Range: -4.4409
Max Act: 4.1908. Min Act: -0.1700
Data Index: 7865461 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4409. Min Range: -4.4409
Max Act: 4.0658. Min Act: -0.1700
Data Index: 6506150 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4409. Min Range: -4.4409
Max Act: 4.0033. Min Act: -0.1700
Data Index: 6136985 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4409. Min Range: -4.4409
Max Act: 3.9720. Min Act: -0.1700
Data Index: 2659980 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4409. Min Range: -4.4409
Max Act: 3.9720. Min Act: -0.1700
Data Index: 7118389 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4409. Min Range: -4.4409
Max Act: 3.9720. Min Act: -0.1700
Data Index: 149955 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4409. Min Range: -4.4409
Max Act: 3.9408. Min Act: -0.1700
Data Index: 8644647 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4409. Min Range: -4.4409
Max Act: 3.9720. Min Act: -0.1700
Data Index: 2244629 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4409. Min Range: -4.4409
Max Act: 3.9408. Min Act: -0.1700
Data Index: 977273 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4409. Min Range: -4.4409
Max Act: 3.9095. Min Act: -0.1700
Data Index: 4200341 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4409. Min Range: -4.4409
Max Act: 3.9408. Min Act: -0.1700
Data Index: 5567832 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4409. Min Range: -4.4409
Max Act: 3.9095. Min Act: -0.1700
Data Index: 3643428 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4409. Min Range: -4.4409
Max Act: 3.9095. Min Act: -0.1700
Data Index: 5432594 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4409. Min Range: -4.4409
Max Act: 3.8782. Min Act: -0.1700
Data Index: 5882313 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4409. Min Range: -4.4409
Max Act: 3.8782. Min Act: -0.1700
Data Index: 4734251 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4409. Min Range: -4.4409
Max Act: 3.8782. Min Act: -0.1700
Data Index: 2644545 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4409. Min Range: -4.4409
Max Act: 3.8470. Min Act: -0.1700
Data Index: 6331527 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4409. Min Range: -4.4409
Max Act: 3.8470. Min Act: -0.1700
Data Index: 2229026 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4409. Min Range: -4.4409
Max Act: 3.8470. Min Act: -0.1700
Data Index: 3996333 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #19