Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3668 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6053. Min Range: -7.6053
Max Act: 7.6053. Min Act: -0.1700
Data Index: 8274363 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6053. Min Range: -7.6053
Max Act: 7.4803. Min Act: -0.1700
Data Index: 6181704 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6053. Min Range: -7.6053
Max Act: 7.4178. Min Act: -0.1700
Data Index: 3118839 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6053. Min Range: -7.6053
Max Act: 7.2928. Min Act: -0.1700
Data Index: 568 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6053. Min Range: -7.6053
Max Act: 7.2928. Min Act: -0.1700
Data Index: 4185358 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6053. Min Range: -7.6053
Max Act: 7.2303. Min Act: -0.1700
Data Index: 7713437 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6053. Min Range: -7.6053
Max Act: 7.1990. Min Act: -0.1700
Data Index: 2985814 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6053. Min Range: -7.6053
Max Act: 7.1678. Min Act: -0.1700
Data Index: 2751365 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6053. Min Range: -7.6053
Max Act: 7.1990. Min Act: -0.1700
Data Index: 1014919 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6053. Min Range: -7.6053
Max Act: 7.1678. Min Act: -0.1700
Data Index: 949143 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6053. Min Range: -7.6053
Max Act: 7.1365. Min Act: -0.1700
Data Index: 1688661 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6053. Min Range: -7.6053
Max Act: 7.1053. Min Act: -0.1700
Data Index: 3296633 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6053. Min Range: -7.6053
Max Act: 7.1053. Min Act: -0.1700
Data Index: 6937330 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6053. Min Range: -7.6053
Max Act: 7.0428. Min Act: -0.1700
Data Index: 3280757 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6053. Min Range: -7.6053
Max Act: 7.1053. Min Act: -0.1700
Data Index: 2007272 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6053. Min Range: -7.6053
Max Act: 7.0428. Min Act: -0.1700
Data Index: 5673527 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6053. Min Range: -7.6053
Max Act: 7.0428. Min Act: -0.1700
Data Index: 444521 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6053. Min Range: -7.6053
Max Act: 7.0428. Min Act: -0.1700
Data Index: 3054806 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6053. Min Range: -7.6053
Max Act: 7.0428. Min Act: -0.1700
Data Index: 6432854 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6053. Min Range: -7.6053
Max Act: 7.0115. Min Act: -0.1700
Data Index: 6121482 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #19