Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4314 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6589. Min Range: -7.6589
Max Act: 7.6589. Min Act: -0.1700
Data Index: 799786 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6589. Min Range: -7.6589
Max Act: 7.5339. Min Act: -0.1700
Data Index: 3873148 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6589. Min Range: -7.6589
Max Act: 7.4714. Min Act: -0.1700
Data Index: 3901910 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6589. Min Range: -7.6589
Max Act: 7.4089. Min Act: -0.1700
Data Index: 3969144 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6589. Min Range: -7.6589
Max Act: 7.3776. Min Act: -0.1700
Data Index: 5607094 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6589. Min Range: -7.6589
Max Act: 7.3776. Min Act: -0.1700
Data Index: 1372709 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6589. Min Range: -7.6589
Max Act: 7.3464. Min Act: -0.1700
Data Index: 5334610 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6589. Min Range: -7.6589
Max Act: 7.3151. Min Act: -0.1700
Data Index: 8750564 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6589. Min Range: -7.6589
Max Act: 7.2526. Min Act: -0.1700
Data Index: 6189105 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6589. Min Range: -7.6589
Max Act: 7.2526. Min Act: -0.1700
Data Index: 8024042 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6589. Min Range: -7.6589
Max Act: 7.2214. Min Act: -0.1700
Data Index: 5550232 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6589. Min Range: -7.6589
Max Act: 7.2214. Min Act: -0.1700
Data Index: 2341872 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6589. Min Range: -7.6589
Max Act: 7.1901. Min Act: -0.1700
Data Index: 6943393 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6589. Min Range: -7.6589
Max Act: 7.1901. Min Act: -0.1700
Data Index: 8529552 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6589. Min Range: -7.6589
Max Act: 7.1589. Min Act: -0.1700
Data Index: 4943797 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6589. Min Range: -7.6589
Max Act: 7.1901. Min Act: -0.1700
Data Index: 4256806 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6589. Min Range: -7.6589
Max Act: 7.2214. Min Act: -0.1700
Data Index: 4948695 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6589. Min Range: -7.6589
Max Act: 7.1276. Min Act: -0.1700
Data Index: 4801148 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6589. Min Range: -7.6589
Max Act: 7.1589. Min Act: -0.1700
Data Index: 6197998 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6589. Min Range: -7.6589
Max Act: 7.1589. Min Act: -0.1700
Data Index: 610348 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #19