Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3741 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3219. Min Range: -5.3219
Max Act: 5.3219. Min Act: -0.1694
Data Index: 502870 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3219. Min Range: -5.3219
Max Act: 5.2281. Min Act: -0.1700
Data Index: 3847153 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3219. Min Range: -5.3219
Max Act: 5.1656. Min Act: -0.1699
Data Index: 8752400 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3219. Min Range: -5.3219
Max Act: 5.1969. Min Act: -0.1700
Data Index: 7337986 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3219. Min Range: -5.3219
Max Act: 5.1656. Min Act: -0.1699
Data Index: 8455325 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3219. Min Range: -5.3219
Max Act: 5.1344. Min Act: -0.1700
Data Index: 7733727 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3219. Min Range: -5.3219
Max Act: 5.1344. Min Act: -0.1700
Data Index: 1195380 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3219. Min Range: -5.3219
Max Act: 5.1031. Min Act: -0.1700
Data Index: 1568674 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3219. Min Range: -5.3219
Max Act: 5.0719. Min Act: -0.1698
Data Index: 7916635 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3219. Min Range: -5.3219
Max Act: 5.1031. Min Act: -0.1697
Data Index: 7860771 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3219. Min Range: -5.3219
Max Act: 5.0406. Min Act: -0.1700
Data Index: 4197688 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3219. Min Range: -5.3219
Max Act: 5.0406. Min Act: -0.1700
Data Index: 1906195 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3219. Min Range: -5.3219
Max Act: 5.0094. Min Act: -0.1700
Data Index: 7311810 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3219. Min Range: -5.3219
Max Act: 5.0094. Min Act: -0.1700
Data Index: 2700500 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3219. Min Range: -5.3219
Max Act: 5.0094. Min Act: -0.1700
Data Index: 8826815 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3219. Min Range: -5.3219
Max Act: 5.0094. Min Act: -0.1700
Data Index: 551436 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3219. Min Range: -5.3219
Max Act: 5.0094. Min Act: -0.1700
Data Index: 7987806 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3219. Min Range: -5.3219
Max Act: 4.9781. Min Act: -0.1700
Data Index: 4245959 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3219. Min Range: -5.3219
Max Act: 4.9781. Min Act: -0.1700
Data Index: 7254177 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3219. Min Range: -5.3219
Max Act: 4.9781. Min Act: -0.1700
Data Index: 4109933 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #19