Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2392 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7120. Min Range: -6.7120
Max Act: 6.7120. Min Act: -0.1700
Data Index: 6766348 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7120. Min Range: -6.7120
Max Act: 6.5870. Min Act: -0.1700
Data Index: 8006843 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7120. Min Range: -6.7120
Max Act: 6.5558. Min Act: -0.1700
Data Index: 810493 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7120. Min Range: -6.7120
Max Act: 6.5245. Min Act: -0.1700
Data Index: 6617931 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7120. Min Range: -6.7120
Max Act: 6.5245. Min Act: -0.1700
Data Index: 6153277 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7120. Min Range: -6.7120
Max Act: 6.4620. Min Act: -0.1700
Data Index: 3871777 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7120. Min Range: -6.7120
Max Act: 6.4933. Min Act: -0.1700
Data Index: 3784667 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7120. Min Range: -6.7120
Max Act: 6.4933. Min Act: -0.1700
Data Index: 552052 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7120. Min Range: -6.7120
Max Act: 6.4620. Min Act: -0.1700
Data Index: 5145589 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7120. Min Range: -6.7120
Max Act: 6.4620. Min Act: -0.1700
Data Index: 1797290 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7120. Min Range: -6.7120
Max Act: 6.4620. Min Act: -0.1700
Data Index: 1182554 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7120. Min Range: -6.7120
Max Act: 6.4308. Min Act: -0.1700
Data Index: 1435162 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7120. Min Range: -6.7120
Max Act: 6.3995. Min Act: -0.1700
Data Index: 3601077 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7120. Min Range: -6.7120
Max Act: 6.3995. Min Act: -0.1700
Data Index: 643652 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7120. Min Range: -6.7120
Max Act: 6.3995. Min Act: -0.1700
Data Index: 6666032 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7120. Min Range: -6.7120
Max Act: 6.3995. Min Act: -0.1700
Data Index: 3688540 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7120. Min Range: -6.7120
Max Act: 6.3683. Min Act: -0.1700
Data Index: 321317 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7120. Min Range: -6.7120
Max Act: 6.3683. Min Act: -0.1700
Data Index: 38512 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7120. Min Range: -6.7120
Max Act: 6.3683. Min Act: -0.1700
Data Index: 1945665 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7120. Min Range: -6.7120
Max Act: 6.3058. Min Act: -0.1700
Data Index: 1841298 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #19