Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5776 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4164. Min Range: -7.4164
Max Act: 7.4164. Min Act: -0.1700
Data Index: 1764809 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4164. Min Range: -7.4164
Max Act: 7.3852. Min Act: -0.1700
Data Index: 1109283 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4164. Min Range: -7.4164
Max Act: 7.2289. Min Act: -0.1700
Data Index: 7314781 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4164. Min Range: -7.4164
Max Act: 7.1977. Min Act: -0.1700
Data Index: 8151460 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4164. Min Range: -7.4164
Max Act: 7.1664. Min Act: -0.1700
Data Index: 4157814 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4164. Min Range: -7.4164
Max Act: 7.1664. Min Act: -0.1700
Data Index: 5340512 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4164. Min Range: -7.4164
Max Act: 7.1039. Min Act: -0.1700
Data Index: 177341 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4164. Min Range: -7.4164
Max Act: 7.0727. Min Act: -0.1700
Data Index: 4556594 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4164. Min Range: -7.4164
Max Act: 7.0727. Min Act: -0.1700
Data Index: 2222232 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4164. Min Range: -7.4164
Max Act: 7.0414. Min Act: -0.1700
Data Index: 883530 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4164. Min Range: -7.4164
Max Act: 7.0414. Min Act: -0.1700
Data Index: 7071006 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4164. Min Range: -7.4164
Max Act: 7.0727. Min Act: -0.1700
Data Index: 7861609 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4164. Min Range: -7.4164
Max Act: 7.0102. Min Act: -0.1700
Data Index: 351252 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4164. Min Range: -7.4164
Max Act: 7.0102. Min Act: -0.1700
Data Index: 789351 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4164. Min Range: -7.4164
Max Act: 7.0102. Min Act: -0.1700
Data Index: 3939638 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4164. Min Range: -7.4164
Max Act: 6.9789. Min Act: -0.1700
Data Index: 3755800 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4164. Min Range: -7.4164
Max Act: 6.9477. Min Act: -0.1700
Data Index: 6736707 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4164. Min Range: -7.4164
Max Act: 6.9477. Min Act: -0.1700
Data Index: 4559374 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4164. Min Range: -7.4164
Max Act: 6.9477. Min Act: -0.1700
Data Index: 2838767 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4164. Min Range: -7.4164
Max Act: 6.9477. Min Act: -0.1700
Data Index: 2673095 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #19