Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4501 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1891. Min Range: -6.1891
Max Act: 6.1891. Min Act: -0.1700
Data Index: 5895885 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1891. Min Range: -6.1891
Max Act: 6.1578. Min Act: -0.1700
Data Index: 7423757 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1891. Min Range: -6.1891
Max Act: 6.1266. Min Act: -0.1700
Data Index: 3173511 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1891. Min Range: -6.1891
Max Act: 6.1578. Min Act: -0.1700
Data Index: 4546831 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1891. Min Range: -6.1891
Max Act: 6.0328. Min Act: -0.1700
Data Index: 473837 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1891. Min Range: -6.1891
Max Act: 6.0016. Min Act: -0.1700
Data Index: 4257028 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1891. Min Range: -6.1891
Max Act: 5.9703. Min Act: -0.1700
Data Index: 561954 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1891. Min Range: -6.1891
Max Act: 5.9703. Min Act: -0.1700
Data Index: 4032252 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1891. Min Range: -6.1891
Max Act: 5.9703. Min Act: -0.1700
Data Index: 1969737 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1891. Min Range: -6.1891
Max Act: 5.9391. Min Act: -0.1700
Data Index: 5341947 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1891. Min Range: -6.1891
Max Act: 5.8766. Min Act: -0.1700
Data Index: 6766030 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1891. Min Range: -6.1891
Max Act: 5.8766. Min Act: -0.1700
Data Index: 3348350 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1891. Min Range: -6.1891
Max Act: 5.8453. Min Act: -0.1700
Data Index: 8596203 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1891. Min Range: -6.1891
Max Act: 5.8453. Min Act: -0.1700
Data Index: 4427217 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1891. Min Range: -6.1891
Max Act: 5.8141. Min Act: -0.1700
Data Index: 2359883 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1891. Min Range: -6.1891
Max Act: 5.8141. Min Act: -0.1700
Data Index: 8148623 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1891. Min Range: -6.1891
Max Act: 5.7828. Min Act: -0.1700
Data Index: 4801730 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1891. Min Range: -6.1891
Max Act: 5.7828. Min Act: -0.1700
Data Index: 6310412 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1891. Min Range: -6.1891
Max Act: 5.7828. Min Act: -0.1700
Data Index: 7144476 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1891. Min Range: -6.1891
Max Act: 5.7828. Min Act: -0.1700
Data Index: 8231694 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #19