Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6015 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4338. Min Range: -8.4338
Max Act: 8.4338. Min Act: -0.1700
Data Index: 4022924 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4338. Min Range: -8.4338
Max Act: 8.4338. Min Act: -0.1700
Data Index: 669359 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4338. Min Range: -8.4338
Max Act: 8.1838. Min Act: -0.1700
Data Index: 1516893 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4338. Min Range: -8.4338
Max Act: 8.0588. Min Act: -0.1700
Data Index: 2218791 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4338. Min Range: -8.4338
Max Act: 8.0588. Min Act: -0.1700
Data Index: 3102011 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4338. Min Range: -8.4338
Max Act: 7.9963. Min Act: -0.1700
Data Index: 4668661 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4338. Min Range: -8.4338
Max Act: 7.9963. Min Act: -0.1700
Data Index: 688198 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4338. Min Range: -8.4338
Max Act: 7.9338. Min Act: -0.1700
Data Index: 8515774 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4338. Min Range: -8.4338
Max Act: 7.8713. Min Act: -0.1700
Data Index: 5404514 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4338. Min Range: -8.4338
Max Act: 7.9338. Min Act: -0.1700
Data Index: 1407953 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4338. Min Range: -8.4338
Max Act: 7.9338. Min Act: -0.1700
Data Index: 5906348 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4338. Min Range: -8.4338
Max Act: 7.8713. Min Act: -0.1700
Data Index: 8018255 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4338. Min Range: -8.4338
Max Act: 7.9338. Min Act: -0.1700
Data Index: 669358 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4338. Min Range: -8.4338
Max Act: 7.8713. Min Act: -0.1700
Data Index: 198476 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4338. Min Range: -8.4338
Max Act: 7.8088. Min Act: -0.1700
Data Index: 451213 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4338. Min Range: -8.4338
Max Act: 7.8088. Min Act: -0.1700
Data Index: 6781374 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4338. Min Range: -8.4338
Max Act: 7.8088. Min Act: -0.1700
Data Index: 210636 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4338. Min Range: -8.4338
Max Act: 7.8088. Min Act: -0.1700
Data Index: 6480025 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4338. Min Range: -8.4338
Max Act: 7.8088. Min Act: -0.1700
Data Index: 410679 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4338. Min Range: -8.4338
Max Act: 7.8088. Min Act: -0.1700
Data Index: 4785865 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #19