Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3658 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1619. Min Range: -6.1619
Max Act: 6.1619. Min Act: -0.1700
Data Index: 2731562 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1619. Min Range: -6.1619
Max Act: 5.8494. Min Act: -0.1700
Data Index: 3077112 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1619. Min Range: -6.1619
Max Act: 5.8494. Min Act: -0.1700
Data Index: 6702323 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1619. Min Range: -6.1619
Max Act: 5.7869. Min Act: -0.1700
Data Index: 5436325 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1619. Min Range: -6.1619
Max Act: 5.7244. Min Act: -0.1700
Data Index: 7252506 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1619. Min Range: -6.1619
Max Act: 5.6932. Min Act: -0.1700
Data Index: 6218125 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1619. Min Range: -6.1619
Max Act: 5.6932. Min Act: -0.1700
Data Index: 6461960 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1619. Min Range: -6.1619
Max Act: 5.6307. Min Act: -0.1700
Data Index: 3176325 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1619. Min Range: -6.1619
Max Act: 5.6307. Min Act: -0.1700
Data Index: 4872136 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1619. Min Range: -6.1619
Max Act: 5.6307. Min Act: -0.1700
Data Index: 4922968 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1619. Min Range: -6.1619
Max Act: 5.6307. Min Act: -0.1700
Data Index: 4570310 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1619. Min Range: -6.1619
Max Act: 5.5682. Min Act: -0.1700
Data Index: 2847547 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1619. Min Range: -6.1619
Max Act: 5.5682. Min Act: -0.1700
Data Index: 3508010 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1619. Min Range: -6.1619
Max Act: 5.5682. Min Act: -0.1700
Data Index: 5409720 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1619. Min Range: -6.1619
Max Act: 5.5682. Min Act: -0.1700
Data Index: 3456515 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1619. Min Range: -6.1619
Max Act: 5.5682. Min Act: -0.1700
Data Index: 6579669 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1619. Min Range: -6.1619
Max Act: 5.5369. Min Act: -0.1700
Data Index: 5583689 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1619. Min Range: -6.1619
Max Act: 5.5369. Min Act: -0.1700
Data Index: 4570311 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1619. Min Range: -6.1619
Max Act: 5.5369. Min Act: -0.1700
Data Index: 4946064 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1619. Min Range: -6.1619
Max Act: 5.5369. Min Act: -0.1700
Data Index: 1640064 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #19