Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1411 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6371. Min Range: -6.6371
Max Act: 6.6371. Min Act: -0.1700
Data Index: 2300290 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6371. Min Range: -6.6371
Max Act: 6.2309. Min Act: -0.1700
Data Index: 7756490 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6371. Min Range: -6.6371
Max Act: 6.1684. Min Act: -0.1700
Data Index: 2087767 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6371. Min Range: -6.6371
Max Act: 6.1684. Min Act: -0.1700
Data Index: 2054871 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6371. Min Range: -6.6371
Max Act: 6.1684. Min Act: -0.1700
Data Index: 7164903 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6371. Min Range: -6.6371
Max Act: 6.1371. Min Act: -0.1700
Data Index: 5984615 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6371. Min Range: -6.6371
Max Act: 6.1059. Min Act: -0.1700
Data Index: 7540772 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6371. Min Range: -6.6371
Max Act: 6.0746. Min Act: -0.1700
Data Index: 4783423 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6371. Min Range: -6.6371
Max Act: 6.0746. Min Act: -0.1700
Data Index: 4043387 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6371. Min Range: -6.6371
Max Act: 6.0746. Min Act: -0.1700
Data Index: 6971828 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6371. Min Range: -6.6371
Max Act: 6.0121. Min Act: -0.1700
Data Index: 268844 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6371. Min Range: -6.6371
Max Act: 6.0434. Min Act: -0.1700
Data Index: 553313 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6371. Min Range: -6.6371
Max Act: 6.0434. Min Act: -0.1700
Data Index: 3067619 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6371. Min Range: -6.6371
Max Act: 6.0434. Min Act: -0.1700
Data Index: 1002206 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6371. Min Range: -6.6371
Max Act: 6.0434. Min Act: -0.1700
Data Index: 1337592 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6371. Min Range: -6.6371
Max Act: 6.0434. Min Act: -0.1700
Data Index: 6755254 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6371. Min Range: -6.6371
Max Act: 6.0121. Min Act: -0.1700
Data Index: 7454292 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6371. Min Range: -6.6371
Max Act: 6.0121. Min Act: -0.1700
Data Index: 2998172 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6371. Min Range: -6.6371
Max Act: 6.0121. Min Act: -0.1700
Data Index: 4138391 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6371. Min Range: -6.6371
Max Act: 6.0121. Min Act: -0.1700
Data Index: 8461885 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #19