Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4998 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2406. Min Range: -6.2406
Max Act: 6.2406. Min Act: -0.1700
Data Index: 3727065 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2406. Min Range: -6.2406
Max Act: 6.1781. Min Act: -0.1700
Data Index: 797828 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2406. Min Range: -6.2406
Max Act: 6.1469. Min Act: -0.1700
Data Index: 4872450 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2406. Min Range: -6.2406
Max Act: 6.0844. Min Act: -0.1700
Data Index: 110677 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2406. Min Range: -6.2406
Max Act: 5.9281. Min Act: -0.1700
Data Index: 3143670 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2406. Min Range: -6.2406
Max Act: 5.8969. Min Act: -0.1700
Data Index: 5902757 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2406. Min Range: -6.2406
Max Act: 5.8969. Min Act: -0.1700
Data Index: 5091277 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2406. Min Range: -6.2406
Max Act: 5.8344. Min Act: -0.1700
Data Index: 6464297 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2406. Min Range: -6.2406
Max Act: 5.8031. Min Act: -0.1700
Data Index: 541656 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2406. Min Range: -6.2406
Max Act: 5.8031. Min Act: -0.1700
Data Index: 3222081 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2406. Min Range: -6.2406
Max Act: 5.8031. Min Act: -0.1700
Data Index: 2752770 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2406. Min Range: -6.2406
Max Act: 5.8031. Min Act: -0.1700
Data Index: 5366351 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2406. Min Range: -6.2406
Max Act: 5.8031. Min Act: -0.1700
Data Index: 5902756 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2406. Min Range: -6.2406
Max Act: 5.7719. Min Act: -0.1700
Data Index: 4736026 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2406. Min Range: -6.2406
Max Act: 5.7719. Min Act: -0.1700
Data Index: 2752769 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2406. Min Range: -6.2406
Max Act: 5.8031. Min Act: -0.1700
Data Index: 5176967 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2406. Min Range: -6.2406
Max Act: 5.7406. Min Act: -0.1700
Data Index: 3281207 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2406. Min Range: -6.2406
Max Act: 5.7406. Min Act: -0.1700
Data Index: 6562174 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2406. Min Range: -6.2406
Max Act: 5.7094. Min Act: -0.1700
Data Index: 1921730 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2406. Min Range: -6.2406
Max Act: 5.7094. Min Act: -0.1700
Data Index: 2711513 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #19