Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2360 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6992. Min Range: -7.6992
Max Act: 7.6992. Min Act: -0.1700
Data Index: 3924049 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6992. Min Range: -7.6992
Max Act: 7.6679. Min Act: -0.1700
Data Index: 6553479 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6992. Min Range: -7.6992
Max Act: 7.3242. Min Act: -0.1700
Data Index: 8783785 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6992. Min Range: -7.6992
Max Act: 7.3242. Min Act: -0.1700
Data Index: 8095276 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6992. Min Range: -7.6992
Max Act: 7.2617. Min Act: -0.1700
Data Index: 4055870 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6992. Min Range: -7.6992
Max Act: 7.2304. Min Act: -0.1700
Data Index: 394458 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6992. Min Range: -7.6992
Max Act: 7.1992. Min Act: -0.1700
Data Index: 7675133 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6992. Min Range: -7.6992
Max Act: 7.1992. Min Act: -0.1700
Data Index: 3729183 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6992. Min Range: -7.6992
Max Act: 7.1367. Min Act: -0.1700
Data Index: 2670082 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6992. Min Range: -7.6992
Max Act: 7.1367. Min Act: -0.1700
Data Index: 3699977 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6992. Min Range: -7.6992
Max Act: 7.1054. Min Act: -0.1700
Data Index: 2444984 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6992. Min Range: -7.6992
Max Act: 7.0742. Min Act: -0.1700
Data Index: 7760749 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6992. Min Range: -7.6992
Max Act: 7.0742. Min Act: -0.1700
Data Index: 8326193 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6992. Min Range: -7.6992
Max Act: 7.0117. Min Act: -0.1700
Data Index: 3699978 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6992. Min Range: -7.6992
Max Act: 7.0117. Min Act: -0.1700
Data Index: 2187134 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6992. Min Range: -7.6992
Max Act: 6.9492. Min Act: -0.1700
Data Index: 8010346 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6992. Min Range: -7.6992
Max Act: 6.9804. Min Act: -0.1700
Data Index: 2999868 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6992. Min Range: -7.6992
Max Act: 6.9492. Min Act: -0.1700
Data Index: 7050646 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6992. Min Range: -7.6992
Max Act: 6.9492. Min Act: -0.1700
Data Index: 6395761 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6992. Min Range: -7.6992
Max Act: 6.9492. Min Act: -0.1700
Data Index: 428214 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #19