Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4253 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1048. Min Range: -8.1048
Max Act: 8.1048. Min Act: -0.1700
Data Index: 7626150 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1048. Min Range: -8.1048
Max Act: 8.0423. Min Act: -0.1700
Data Index: 8318616 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1048. Min Range: -8.1048
Max Act: 8.0423. Min Act: -0.1700
Data Index: 8250859 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1048. Min Range: -8.1048
Max Act: 7.8548. Min Act: -0.1700
Data Index: 5965880 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1048. Min Range: -8.1048
Max Act: 7.8548. Min Act: -0.1700
Data Index: 1779633 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1048. Min Range: -8.1048
Max Act: 7.8548. Min Act: -0.1700
Data Index: 585936 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1048. Min Range: -8.1048
Max Act: 7.7923. Min Act: -0.1700
Data Index: 7460566 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1048. Min Range: -8.1048
Max Act: 7.7923. Min Act: -0.1700
Data Index: 7656816 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1048. Min Range: -8.1048
Max Act: 7.6673. Min Act: -0.1700
Data Index: 3337106 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1048. Min Range: -8.1048
Max Act: 7.7298. Min Act: -0.1700
Data Index: 3489701 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1048. Min Range: -8.1048
Max Act: 7.7298. Min Act: -0.1700
Data Index: 1519869 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1048. Min Range: -8.1048
Max Act: 7.7298. Min Act: -0.1700
Data Index: 6356281 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1048. Min Range: -8.1048
Max Act: 7.7298. Min Act: -0.1700
Data Index: 6905078 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1048. Min Range: -8.1048
Max Act: 7.6673. Min Act: -0.1700
Data Index: 6262859 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1048. Min Range: -8.1048
Max Act: 7.6673. Min Act: -0.1700
Data Index: 4608228 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1048. Min Range: -8.1048
Max Act: 7.6673. Min Act: -0.1700
Data Index: 838000 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1048. Min Range: -8.1048
Max Act: 7.6673. Min Act: -0.1700
Data Index: 5250981 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1048. Min Range: -8.1048
Max Act: 7.6048. Min Act: -0.1700
Data Index: 243207 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1048. Min Range: -8.1048
Max Act: 7.6048. Min Act: -0.1700
Data Index: 1675071 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1048. Min Range: -8.1048
Max Act: 7.6048. Min Act: -0.1700
Data Index: 5976727 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #19