Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3284 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2202. Min Range: -6.2202
Max Act: 6.2202. Min Act: -0.1699
Data Index: 7963131 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2202. Min Range: -6.2202
Max Act: 6.0640. Min Act: -0.1697
Data Index: 4180152 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2202. Min Range: -6.2202
Max Act: 6.0327. Min Act: -0.1700
Data Index: 7900475 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2202. Min Range: -6.2202
Max Act: 6.0015. Min Act: -0.1700
Data Index: 5494955 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2202. Min Range: -6.2202
Max Act: 5.9702. Min Act: -0.1700
Data Index: 8309830 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2202. Min Range: -6.2202
Max Act: 5.9702. Min Act: -0.1700
Data Index: 1619861 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2202. Min Range: -6.2202
Max Act: 5.9702. Min Act: -0.1700
Data Index: 1508360 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2202. Min Range: -6.2202
Max Act: 5.9702. Min Act: -0.1608
Data Index: 3277095 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2202. Min Range: -6.2202
Max Act: 6.0015. Min Act: -0.1699
Data Index: 6914521 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2202. Min Range: -6.2202
Max Act: 5.9702. Min Act: -0.1698
Data Index: 4240974 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2202. Min Range: -6.2202
Max Act: 5.9390. Min Act: -0.1700
Data Index: 6483898 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2202. Min Range: -6.2202
Max Act: 5.9390. Min Act: -0.1700
Data Index: 6908978 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2202. Min Range: -6.2202
Max Act: 5.9390. Min Act: -0.1699
Data Index: 4451751 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2202. Min Range: -6.2202
Max Act: 5.9390. Min Act: -0.1700
Data Index: 7321370 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2202. Min Range: -6.2202
Max Act: 5.9390. Min Act: -0.1700
Data Index: 4217111 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2202. Min Range: -6.2202
Max Act: 5.9077. Min Act: -0.1700
Data Index: 526538 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2202. Min Range: -6.2202
Max Act: 5.9077. Min Act: -0.1700
Data Index: 1556957 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2202. Min Range: -6.2202
Max Act: 5.9077. Min Act: -0.1700
Data Index: 1486392 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2202. Min Range: -6.2202
Max Act: 5.9077. Min Act: -0.1700
Data Index: 7536653 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2202. Min Range: -6.2202
Max Act: 5.9077. Min Act: -0.1700
Data Index: 1934143 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #19