Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2848 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6948. Min Range: -6.6948
Max Act: 6.6948. Min Act: -0.1700
Data Index: 7474098 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6948. Min Range: -6.6948
Max Act: 6.6011. Min Act: -0.1700
Data Index: 8769612 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6948. Min Range: -6.6948
Max Act: 6.4136. Min Act: -0.1700
Data Index: 5397929 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6948. Min Range: -6.6948
Max Act: 6.3511. Min Act: -0.1700
Data Index: 7981226 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6948. Min Range: -6.6948
Max Act: 6.2886. Min Act: -0.1700
Data Index: 2485507 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6948. Min Range: -6.6948
Max Act: 6.2573. Min Act: -0.1700
Data Index: 4924823 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6948. Min Range: -6.6948
Max Act: 6.2573. Min Act: -0.1700
Data Index: 8814605 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6948. Min Range: -6.6948
Max Act: 6.2261. Min Act: -0.1700
Data Index: 1790880 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6948. Min Range: -6.6948
Max Act: 6.1948. Min Act: -0.1700
Data Index: 2607924 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6948. Min Range: -6.6948
Max Act: 6.1948. Min Act: -0.1700
Data Index: 2975109 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6948. Min Range: -6.6948
Max Act: 6.1011. Min Act: -0.1700
Data Index: 6335961 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6948. Min Range: -6.6948
Max Act: 6.1011. Min Act: -0.1700
Data Index: 8696583 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6948. Min Range: -6.6948
Max Act: 6.1323. Min Act: -0.1700
Data Index: 2520156 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6948. Min Range: -6.6948
Max Act: 6.1011. Min Act: -0.1700
Data Index: 2934989 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6948. Min Range: -6.6948
Max Act: 6.1011. Min Act: -0.1700
Data Index: 2338663 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6948. Min Range: -6.6948
Max Act: 6.0698. Min Act: -0.1700
Data Index: 1053355 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6948. Min Range: -6.6948
Max Act: 6.0698. Min Act: -0.1700
Data Index: 4396100 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6948. Min Range: -6.6948
Max Act: 6.0698. Min Act: -0.1700
Data Index: 1066878 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6948. Min Range: -6.6948
Max Act: 6.0698. Min Act: -0.1700
Data Index: 6825199 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6948. Min Range: -6.6948
Max Act: 6.0698. Min Act: -0.1700
Data Index: 6917391 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #19