Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3163 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7493. Min Range: -5.7493
Max Act: 5.7493. Min Act: -0.1700
Data Index: 5002054 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7493. Min Range: -5.7493
Max Act: 5.6868. Min Act: -0.1700
Data Index: 7246644 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7493. Min Range: -5.7493
Max Act: 5.6555. Min Act: -0.1700
Data Index: 3554245 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7493. Min Range: -5.7493
Max Act: 5.6555. Min Act: -0.1700
Data Index: 1665301 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7493. Min Range: -5.7493
Max Act: 5.6243. Min Act: -0.1700
Data Index: 4488654 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7493. Min Range: -5.7493
Max Act: 5.6243. Min Act: -0.1700
Data Index: 7629685 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7493. Min Range: -5.7493
Max Act: 5.6243. Min Act: -0.1700
Data Index: 3433712 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7493. Min Range: -5.7493
Max Act: 5.6243. Min Act: -0.1700
Data Index: 7224240 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7493. Min Range: -5.7493
Max Act: 5.5930. Min Act: -0.1700
Data Index: 3619274 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7493. Min Range: -5.7493
Max Act: 5.5930. Min Act: -0.1700
Data Index: 6012807 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7493. Min Range: -5.7493
Max Act: 5.5618. Min Act: -0.1700
Data Index: 5134392 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7493. Min Range: -5.7493
Max Act: 5.5930. Min Act: -0.1700
Data Index: 6978550 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7493. Min Range: -5.7493
Max Act: 5.5930. Min Act: -0.1700
Data Index: 3674604 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7493. Min Range: -5.7493
Max Act: 5.5930. Min Act: -0.1700
Data Index: 4418332 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7493. Min Range: -5.7493
Max Act: 5.5930. Min Act: -0.1700
Data Index: 49521 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7493. Min Range: -5.7493
Max Act: 5.5618. Min Act: -0.1700
Data Index: 143193 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7493. Min Range: -5.7493
Max Act: 5.5618. Min Act: -0.1700
Data Index: 4783669 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7493. Min Range: -5.7493
Max Act: 5.5618. Min Act: -0.1700
Data Index: 4433409 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7493. Min Range: -5.7493
Max Act: 5.5618. Min Act: -0.1700
Data Index: 56508 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7493. Min Range: -5.7493
Max Act: 5.5618. Min Act: -0.1700
Data Index: 408779 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #19