Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4822 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1409. Min Range: -7.1409
Max Act: 7.1409. Min Act: -0.1700
Data Index: 913532 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1409. Min Range: -7.1409
Max Act: 7.1409. Min Act: -0.1700
Data Index: 78530 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1409. Min Range: -7.1409
Max Act: 7.0471. Min Act: -0.1700
Data Index: 2359745 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1409. Min Range: -7.1409
Max Act: 6.9221. Min Act: -0.1700
Data Index: 6472755 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1409. Min Range: -7.1409
Max Act: 6.8909. Min Act: -0.1700
Data Index: 4583388 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1409. Min Range: -7.1409
Max Act: 6.8596. Min Act: -0.1700
Data Index: 6722898 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1409. Min Range: -7.1409
Max Act: 6.7659. Min Act: -0.1700
Data Index: 8556612 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1409. Min Range: -7.1409
Max Act: 6.7346. Min Act: -0.1700
Data Index: 1313273 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1409. Min Range: -7.1409
Max Act: 6.7659. Min Act: -0.1700
Data Index: 6477236 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1409. Min Range: -7.1409
Max Act: 6.7346. Min Act: -0.1700
Data Index: 5093001 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1409. Min Range: -7.1409
Max Act: 6.7346. Min Act: -0.1700
Data Index: 4716943 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1409. Min Range: -7.1409
Max Act: 6.6721. Min Act: -0.1700
Data Index: 3414659 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1409. Min Range: -7.1409
Max Act: 6.6409. Min Act: -0.1700
Data Index: 4093914 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1409. Min Range: -7.1409
Max Act: 6.6409. Min Act: -0.1700
Data Index: 8324010 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1409. Min Range: -7.1409
Max Act: 6.6721. Min Act: -0.1700
Data Index: 502539 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1409. Min Range: -7.1409
Max Act: 6.6409. Min Act: -0.1700
Data Index: 4093912 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1409. Min Range: -7.1409
Max Act: 6.6409. Min Act: -0.1700
Data Index: 7108381 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1409. Min Range: -7.1409
Max Act: 6.6096. Min Act: -0.1700
Data Index: 4162605 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1409. Min Range: -7.1409
Max Act: 6.6096. Min Act: -0.1700
Data Index: 1533248 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1409. Min Range: -7.1409
Max Act: 6.6096. Min Act: -0.1700
Data Index: 6951787 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #19