Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2661 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2760. Min Range: -6.2760
Max Act: 6.2760. Min Act: -0.1700
Data Index: 2039922 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2760. Min Range: -6.2760
Max Act: 6.0572. Min Act: -0.1700
Data Index: 5707637 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2760. Min Range: -6.2760
Max Act: 5.9635. Min Act: -0.1700
Data Index: 6896268 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2760. Min Range: -6.2760
Max Act: 5.9010. Min Act: -0.1700
Data Index: 1497147 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2760. Min Range: -6.2760
Max Act: 5.9322. Min Act: -0.1700
Data Index: 8428399 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2760. Min Range: -6.2760
Max Act: 5.9010. Min Act: -0.1700
Data Index: 1336311 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2760. Min Range: -6.2760
Max Act: 5.9322. Min Act: -0.1700
Data Index: 8010960 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2760. Min Range: -6.2760
Max Act: 5.9010. Min Act: -0.1700
Data Index: 3849188 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2760. Min Range: -6.2760
Max Act: 5.9010. Min Act: -0.1700
Data Index: 534619 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2760. Min Range: -6.2760
Max Act: 5.9010. Min Act: -0.1700
Data Index: 5292327 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2760. Min Range: -6.2760
Max Act: 5.8697. Min Act: -0.1700
Data Index: 2588377 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2760. Min Range: -6.2760
Max Act: 5.7760. Min Act: -0.1700
Data Index: 8179865 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2760. Min Range: -6.2760
Max Act: 5.7760. Min Act: -0.1700
Data Index: 7774886 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2760. Min Range: -6.2760
Max Act: 5.7135. Min Act: -0.1700
Data Index: 4602610 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2760. Min Range: -6.2760
Max Act: 5.7447. Min Act: -0.1700
Data Index: 2648537 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2760. Min Range: -6.2760
Max Act: 5.7135. Min Act: -0.1700
Data Index: 2061555 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2760. Min Range: -6.2760
Max Act: 5.7135. Min Act: -0.1700
Data Index: 277440 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2760. Min Range: -6.2760
Max Act: 5.6822. Min Act: -0.1700
Data Index: 8078253 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2760. Min Range: -6.2760
Max Act: 5.6822. Min Act: -0.1700
Data Index: 8507200 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2760. Min Range: -6.2760
Max Act: 5.6822. Min Act: -0.1700
Data Index: 2900221 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #19