Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2457 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2977. Min Range: -9.2977
Max Act: 9.2977. Min Act: -0.1700
Data Index: 1847425 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2977. Min Range: -9.2977
Max Act: 9.0477. Min Act: -0.1700
Data Index: 4856334 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2977. Min Range: -9.2977
Max Act: 8.8602. Min Act: -0.1700
Data Index: 1651390 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2977. Min Range: -9.2977
Max Act: 8.7352. Min Act: -0.1700
Data Index: 1587084 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2977. Min Range: -9.2977
Max Act: 8.6727. Min Act: -0.1700
Data Index: 8780280 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2977. Min Range: -9.2977
Max Act: 8.6727. Min Act: -0.1700
Data Index: 2086677 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2977. Min Range: -9.2977
Max Act: 8.6102. Min Act: -0.1700
Data Index: 7729022 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2977. Min Range: -9.2977
Max Act: 8.6102. Min Act: -0.1700
Data Index: 4810963 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2977. Min Range: -9.2977
Max Act: 8.6102. Min Act: -0.1700
Data Index: 897437 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2977. Min Range: -9.2977
Max Act: 8.6102. Min Act: -0.1700
Data Index: 5184951 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2977. Min Range: -9.2977
Max Act: 8.6102. Min Act: -0.1700
Data Index: 6281715 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2977. Min Range: -9.2977
Max Act: 8.5477. Min Act: -0.1700
Data Index: 7619839 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2977. Min Range: -9.2977
Max Act: 8.4852. Min Act: -0.1700
Data Index: 299987 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2977. Min Range: -9.2977
Max Act: 8.4852. Min Act: -0.1700
Data Index: 600271 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2977. Min Range: -9.2977
Max Act: 8.4227. Min Act: -0.1700
Data Index: 1061682 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2977. Min Range: -9.2977
Max Act: 8.4227. Min Act: -0.1700
Data Index: 7685092 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2977. Min Range: -9.2977
Max Act: 8.4227. Min Act: -0.1700
Data Index: 4968853 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2977. Min Range: -9.2977
Max Act: 8.4227. Min Act: -0.1700
Data Index: 2007811 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2977. Min Range: -9.2977
Max Act: 8.4227. Min Act: -0.1700
Data Index: 2312194 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2977. Min Range: -9.2977
Max Act: 8.4227. Min Act: -0.1700
Data Index: 1320672 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #19