Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3549 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1207. Min Range: -6.1207
Max Act: 6.1207. Min Act: -0.1700
Data Index: 5370985 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1207. Min Range: -6.1207
Max Act: 5.9645. Min Act: -0.1700
Data Index: 2529003 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1207. Min Range: -6.1207
Max Act: 5.7770. Min Act: -0.1700
Data Index: 7129600 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1207. Min Range: -6.1207
Max Act: 5.7457. Min Act: -0.1700
Data Index: 6810494 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1207. Min Range: -6.1207
Max Act: 5.7457. Min Act: -0.1700
Data Index: 3011302 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1207. Min Range: -6.1207
Max Act: 5.6832. Min Act: -0.1700
Data Index: 430593 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1207. Min Range: -6.1207
Max Act: 5.6832. Min Act: -0.1700
Data Index: 1949045 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1207. Min Range: -6.1207
Max Act: 5.6520. Min Act: -0.1700
Data Index: 7761415 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1207. Min Range: -6.1207
Max Act: 5.6520. Min Act: -0.1700
Data Index: 6766697 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1207. Min Range: -6.1207
Max Act: 5.6207. Min Act: -0.1700
Data Index: 6544029 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1207. Min Range: -6.1207
Max Act: 5.6207. Min Act: -0.1700
Data Index: 1543536 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1207. Min Range: -6.1207
Max Act: 5.6207. Min Act: -0.1700
Data Index: 1121910 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1207. Min Range: -6.1207
Max Act: 5.5895. Min Act: -0.1700
Data Index: 6181679 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1207. Min Range: -6.1207
Max Act: 5.6207. Min Act: -0.1700
Data Index: 8323095 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1207. Min Range: -6.1207
Max Act: 5.5895. Min Act: -0.1700
Data Index: 552100 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1207. Min Range: -6.1207
Max Act: 5.5582. Min Act: -0.1700
Data Index: 8418489 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1207. Min Range: -6.1207
Max Act: 5.5895. Min Act: -0.1700
Data Index: 2233126 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1207. Min Range: -6.1207
Max Act: 5.5895. Min Act: -0.1700
Data Index: 378651 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1207. Min Range: -6.1207
Max Act: 5.5895. Min Act: -0.1700
Data Index: 5957789 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1207. Min Range: -6.1207
Max Act: 5.5582. Min Act: -0.1700
Data Index: 4959938 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #19