Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3428 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4794. Min Range: -6.4794
Max Act: 6.4794. Min Act: -0.1700
Data Index: 5589694 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4794. Min Range: -6.4794
Max Act: 6.2919. Min Act: -0.1700
Data Index: 677765 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4794. Min Range: -6.4794
Max Act: 6.2606. Min Act: -0.1700
Data Index: 1138111 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4794. Min Range: -6.4794
Max Act: 6.1981. Min Act: -0.1700
Data Index: 4314043 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4794. Min Range: -6.4794
Max Act: 6.1669. Min Act: -0.1700
Data Index: 6332612 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4794. Min Range: -6.4794
Max Act: 6.1356. Min Act: -0.1700
Data Index: 3745711 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4794. Min Range: -6.4794
Max Act: 6.1044. Min Act: -0.1700
Data Index: 1028679 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4794. Min Range: -6.4794
Max Act: 6.0731. Min Act: -0.1700
Data Index: 3763249 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4794. Min Range: -6.4794
Max Act: 6.0419. Min Act: -0.1700
Data Index: 1138117 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4794. Min Range: -6.4794
Max Act: 6.0106. Min Act: -0.1700
Data Index: 340343 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4794. Min Range: -6.4794
Max Act: 5.9794. Min Act: -0.1700
Data Index: 5847153 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4794. Min Range: -6.4794
Max Act: 5.9794. Min Act: -0.1700
Data Index: 677771 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4794. Min Range: -6.4794
Max Act: 5.8856. Min Act: -0.1700
Data Index: 4314047 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4794. Min Range: -6.4794
Max Act: 5.8856. Min Act: -0.1700
Data Index: 3531836 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4794. Min Range: -6.4794
Max Act: 5.8856. Min Act: -0.1700
Data Index: 2647193 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4794. Min Range: -6.4794
Max Act: 5.8856. Min Act: -0.1700
Data Index: 408241 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4794. Min Range: -6.4794
Max Act: 5.8544. Min Act: -0.1700
Data Index: 8133898 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4794. Min Range: -6.4794
Max Act: 5.8231. Min Act: -0.1700
Data Index: 7713523 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4794. Min Range: -6.4794
Max Act: 5.8231. Min Act: -0.1700
Data Index: 3725908 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4794. Min Range: -6.4794
Max Act: 5.8231. Min Act: -0.1700
Data Index: 1839638 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #19