Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4066 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2738. Min Range: -5.2738
Max Act: 5.2738. Min Act: -0.1700
Data Index: 1695230 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2738. Min Range: -5.2738
Max Act: 5.2738. Min Act: -0.1700
Data Index: 6897477 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2738. Min Range: -5.2738
Max Act: 5.2425. Min Act: -0.1700
Data Index: 6694100 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2738. Min Range: -5.2738
Max Act: 5.2113. Min Act: -0.1700
Data Index: 6694098 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2738. Min Range: -5.2738
Max Act: 5.2113. Min Act: -0.1700
Data Index: 1470262 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2738. Min Range: -5.2738
Max Act: 5.2113. Min Act: -0.1700
Data Index: 7485274 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2738. Min Range: -5.2738
Max Act: 5.1800. Min Act: -0.1700
Data Index: 7220478 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2738. Min Range: -5.2738
Max Act: 5.1800. Min Act: -0.1700
Data Index: 4998300 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2738. Min Range: -5.2738
Max Act: 5.1800. Min Act: -0.1700
Data Index: 336961 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2738. Min Range: -5.2738
Max Act: 5.1800. Min Act: -0.1700
Data Index: 8585965 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2738. Min Range: -5.2738
Max Act: 5.1800. Min Act: -0.1700
Data Index: 1697749 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2738. Min Range: -5.2738
Max Act: 5.1488. Min Act: -0.1700
Data Index: 2397198 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2738. Min Range: -5.2738
Max Act: 5.1488. Min Act: -0.1700
Data Index: 5057129 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2738. Min Range: -5.2738
Max Act: 5.1488. Min Act: -0.1700
Data Index: 4392614 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2738. Min Range: -5.2738
Max Act: 5.1488. Min Act: -0.1700
Data Index: 7220479 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2738. Min Range: -5.2738
Max Act: 5.1175. Min Act: -0.1700
Data Index: 519209 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2738. Min Range: -5.2738
Max Act: 5.0863. Min Act: -0.1700
Data Index: 6392629 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2738. Min Range: -5.2738
Max Act: 5.1175. Min Act: -0.1700
Data Index: 1374352 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2738. Min Range: -5.2738
Max Act: 5.1175. Min Act: -0.1700
Data Index: 4407952 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2738. Min Range: -5.2738
Max Act: 5.1175. Min Act: -0.1700
Data Index: 7107874 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #19