Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3852 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2133. Min Range: -5.2133
Max Act: 5.2133. Min Act: -0.1700
Data Index: 1314297 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2133. Min Range: -5.2133
Max Act: 5.0258. Min Act: -0.1700
Data Index: 1414409 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2133. Min Range: -5.2133
Max Act: 4.9321. Min Act: -0.1700
Data Index: 4097705 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2133. Min Range: -5.2133
Max Act: 4.8696. Min Act: -0.1700
Data Index: 5721871 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2133. Min Range: -5.2133
Max Act: 4.7446. Min Act: -0.1700
Data Index: 4508833 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2133. Min Range: -5.2133
Max Act: 4.7133. Min Act: -0.1700
Data Index: 109822 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2133. Min Range: -5.2133
Max Act: 4.7446. Min Act: -0.1700
Data Index: 4892341 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2133. Min Range: -5.2133
Max Act: 4.6821. Min Act: -0.1700
Data Index: 4364971 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2133. Min Range: -5.2133
Max Act: 4.6821. Min Act: -0.1700
Data Index: 7848602 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2133. Min Range: -5.2133
Max Act: 4.6821. Min Act: -0.1700
Data Index: 2162981 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2133. Min Range: -5.2133
Max Act: 4.6821. Min Act: -0.1700
Data Index: 795621 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2133. Min Range: -5.2133
Max Act: 4.6821. Min Act: -0.1700
Data Index: 2995327 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2133. Min Range: -5.2133
Max Act: 4.6821. Min Act: -0.1700
Data Index: 1663776 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2133. Min Range: -5.2133
Max Act: 4.6508. Min Act: -0.1700
Data Index: 4750975 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2133. Min Range: -5.2133
Max Act: 4.6508. Min Act: -0.1700
Data Index: 3043092 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2133. Min Range: -5.2133
Max Act: 4.6196. Min Act: -0.1700
Data Index: 5060649 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2133. Min Range: -5.2133
Max Act: 4.6196. Min Act: -0.1700
Data Index: 2631790 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2133. Min Range: -5.2133
Max Act: 4.6196. Min Act: -0.1700
Data Index: 2333294 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2133. Min Range: -5.2133
Max Act: 4.5883. Min Act: -0.1700
Data Index: 4578582 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2133. Min Range: -5.2133
Max Act: 4.6196. Min Act: -0.1700
Data Index: 4750973 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #19