Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4639 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3628. Min Range: -4.3628
Max Act: 4.3628. Min Act: -0.1700
Data Index: 354683 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3628. Min Range: -4.3628
Max Act: 3.9877. Min Act: -0.1700
Data Index: 3754918 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3628. Min Range: -4.3628
Max Act: 3.8939. Min Act: -0.1700
Data Index: 2061529 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3628. Min Range: -4.3628
Max Act: 3.8627. Min Act: -0.1700
Data Index: 7094887 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3628. Min Range: -4.3628
Max Act: 3.8314. Min Act: -0.1700
Data Index: 541310 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3628. Min Range: -4.3628
Max Act: 3.8158. Min Act: -0.1700
Data Index: 5622791 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3628. Min Range: -4.3628
Max Act: 3.8314. Min Act: -0.1700
Data Index: 4977620 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3628. Min Range: -4.3628
Max Act: 3.8001. Min Act: -0.1700
Data Index: 4273435 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3628. Min Range: -4.3628
Max Act: 3.8001. Min Act: -0.1700
Data Index: 2728797 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3628. Min Range: -4.3628
Max Act: 3.7845. Min Act: -0.1700
Data Index: 4308180 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3628. Min Range: -4.3628
Max Act: 3.7845. Min Act: -0.1700
Data Index: 3847069 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3628. Min Range: -4.3628
Max Act: 3.7845. Min Act: -0.1700
Data Index: 6363025 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3628. Min Range: -4.3628
Max Act: 3.7689. Min Act: -0.1700
Data Index: 3780899 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3628. Min Range: -4.3628
Max Act: 3.7689. Min Act: -0.1700
Data Index: 3798329 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3628. Min Range: -4.3628
Max Act: 3.7532. Min Act: -0.1700
Data Index: 2519173 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3628. Min Range: -4.3628
Max Act: 3.7689. Min Act: -0.1700
Data Index: 7425755 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3628. Min Range: -4.3628
Max Act: 3.7376. Min Act: -0.1700
Data Index: 3513353 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3628. Min Range: -4.3628
Max Act: 3.7376. Min Act: -0.1700
Data Index: 2934319 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3628. Min Range: -4.3628
Max Act: 3.7376. Min Act: -0.1700
Data Index: 2977575 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3628. Min Range: -4.3628
Max Act: 3.7219. Min Act: -0.1700
Data Index: 8142561 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #19