Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3469 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1606. Min Range: -4.1606
Max Act: 4.1606. Min Act: -0.1700
Data Index: 6505808 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1606. Min Range: -4.1606
Max Act: 4.1294. Min Act: -0.1700
Data Index: 6213439 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1606. Min Range: -4.1606
Max Act: 4.0981. Min Act: -0.1700
Data Index: 6158501 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1606. Min Range: -4.1606
Max Act: 4.1294. Min Act: -0.1700
Data Index: 2448445 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1606. Min Range: -4.1606
Max Act: 4.0668. Min Act: -0.1700
Data Index: 7291276 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1606. Min Range: -4.1606
Max Act: 4.0356. Min Act: -0.1700
Data Index: 4566624 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1606. Min Range: -4.1606
Max Act: 4.0043. Min Act: -0.1700
Data Index: 3253714 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1606. Min Range: -4.1606
Max Act: 4.0043. Min Act: -0.1700
Data Index: 2125207 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1606. Min Range: -4.1606
Max Act: 3.9731. Min Act: -0.1700
Data Index: 5714637 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1606. Min Range: -4.1606
Max Act: 3.9731. Min Act: -0.1700
Data Index: 2057596 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1606. Min Range: -4.1606
Max Act: 3.9731. Min Act: -0.1700
Data Index: 1930024 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1606. Min Range: -4.1606
Max Act: 3.9731. Min Act: -0.1700
Data Index: 3954020 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1606. Min Range: -4.1606
Max Act: 3.9105. Min Act: -0.1700
Data Index: 6892625 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1606. Min Range: -4.1606
Max Act: 3.9418. Min Act: -0.1700
Data Index: 836350 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1606. Min Range: -4.1606
Max Act: 3.9418. Min Act: -0.1700
Data Index: 3287372 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1606. Min Range: -4.1606
Max Act: 3.9418. Min Act: -0.1700
Data Index: 2265417 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1606. Min Range: -4.1606
Max Act: 3.9418. Min Act: -0.1700
Data Index: 366520 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1606. Min Range: -4.1606
Max Act: 3.9418. Min Act: -0.1700
Data Index: 6377681 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1606. Min Range: -4.1606
Max Act: 3.9105. Min Act: -0.1700
Data Index: 1201088 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1606. Min Range: -4.1606
Max Act: 3.9105. Min Act: -0.1700
Data Index: 929688 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #19