Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4294 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 16.1001. Min Range: -16.1001
Max Act: 16.1001. Min Act: -0.1700
Data Index: 6291472 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 16.1001. Min Range: -16.1001
Max Act: 15.0376. Min Act: -0.1700
Data Index: 2983101 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 16.1001. Min Range: -16.1001
Max Act: 14.9126. Min Act: -0.1700
Data Index: 3278368 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 16.1001. Min Range: -16.1001
Max Act: 14.9126. Min Act: -0.1700
Data Index: 3601891 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 16.1001. Min Range: -16.1001
Max Act: 14.7876. Min Act: -0.1700
Data Index: 7192815 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 16.1001. Min Range: -16.1001
Max Act: 14.7876. Min Act: -0.1700
Data Index: 1384622 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 16.1001. Min Range: -16.1001
Max Act: 14.7876. Min Act: -0.1700
Data Index: 7062192 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 16.1001. Min Range: -16.1001
Max Act: 14.7251. Min Act: -0.1700
Data Index: 4183668 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 16.1001. Min Range: -16.1001
Max Act: 14.6626. Min Act: -0.1700
Data Index: 3450029 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 16.1001. Min Range: -16.1001
Max Act: 14.7251. Min Act: -0.1700
Data Index: 5012551 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 16.1001. Min Range: -16.1001
Max Act: 14.6001. Min Act: -0.1700
Data Index: 1265331 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 16.1001. Min Range: -16.1001
Max Act: 14.6001. Min Act: -0.1700
Data Index: 6329283 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 16.1001. Min Range: -16.1001
Max Act: 14.6001. Min Act: -0.1700
Data Index: 7577266 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 16.1001. Min Range: -16.1001
Max Act: 14.6001. Min Act: -0.1700
Data Index: 3568074 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 16.1001. Min Range: -16.1001
Max Act: 14.5376. Min Act: -0.1700
Data Index: 5642680 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 16.1001. Min Range: -16.1001
Max Act: 14.5376. Min Act: -0.1700
Data Index: 8221984 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 16.1001. Min Range: -16.1001
Max Act: 14.5376. Min Act: -0.1700
Data Index: 5193712 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 16.1001. Min Range: -16.1001
Max Act: 14.5376. Min Act: -0.1700
Data Index: 1261316 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 16.1001. Min Range: -16.1001
Max Act: 14.4751. Min Act: -0.1700
Data Index: 6827638 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 16.1001. Min Range: -16.1001
Max Act: 14.4751. Min Act: -0.1700
Data Index: 4782319 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #19