Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6395 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2955. Min Range: -6.2955
Max Act: 6.2955. Min Act: -0.1700
Data Index: 6953057 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2955. Min Range: -6.2955
Max Act: 6.2018. Min Act: -0.1700
Data Index: 5829040 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2955. Min Range: -6.2955
Max Act: 6.1393. Min Act: -0.1700
Data Index: 5349874 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2955. Min Range: -6.2955
Max Act: 6.1080. Min Act: -0.1700
Data Index: 3317373 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2955. Min Range: -6.2955
Max Act: 6.1080. Min Act: -0.1700
Data Index: 823651 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2955. Min Range: -6.2955
Max Act: 6.1080. Min Act: -0.1700
Data Index: 2540511 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2955. Min Range: -6.2955
Max Act: 6.0768. Min Act: -0.1700
Data Index: 5658533 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2955. Min Range: -6.2955
Max Act: 6.0768. Min Act: -0.1700
Data Index: 6358136 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2955. Min Range: -6.2955
Max Act: 6.0455. Min Act: -0.1700
Data Index: 4694200 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2955. Min Range: -6.2955
Max Act: 6.0455. Min Act: -0.1700
Data Index: 3297327 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2955. Min Range: -6.2955
Max Act: 6.0455. Min Act: -0.1700
Data Index: 814171 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2955. Min Range: -6.2955
Max Act: 6.0143. Min Act: -0.1700
Data Index: 1936727 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2955. Min Range: -6.2955
Max Act: 6.0143. Min Act: -0.1700
Data Index: 1062156 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2955. Min Range: -6.2955
Max Act: 6.0143. Min Act: -0.1700
Data Index: 6540657 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2955. Min Range: -6.2955
Max Act: 5.9830. Min Act: -0.1700
Data Index: 3518010 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2955. Min Range: -6.2955
Max Act: 6.0143. Min Act: -0.1700
Data Index: 3601033 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2955. Min Range: -6.2955
Max Act: 6.0143. Min Act: -0.1700
Data Index: 122836 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2955. Min Range: -6.2955
Max Act: 5.9830. Min Act: -0.1700
Data Index: 612103 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2955. Min Range: -6.2955
Max Act: 5.9830. Min Act: -0.1700
Data Index: 3579545 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2955. Min Range: -6.2955
Max Act: 5.9518. Min Act: -0.1700
Data Index: 7814790 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #19