Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2015 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5773. Min Range: -5.5773
Max Act: 5.5773. Min Act: -0.1700
Data Index: 8146851 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5773. Min Range: -5.5773
Max Act: 5.5773. Min Act: -0.1700
Data Index: 8788284 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5773. Min Range: -5.5773
Max Act: 5.5148. Min Act: -0.1700
Data Index: 997083 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5773. Min Range: -5.5773
Max Act: 5.5461. Min Act: -0.1700
Data Index: 7973517 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5773. Min Range: -5.5773
Max Act: 5.5148. Min Act: -0.1700
Data Index: 2564030 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5773. Min Range: -5.5773
Max Act: 5.4523. Min Act: -0.1700
Data Index: 2020424 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5773. Min Range: -5.5773
Max Act: 5.4211. Min Act: -0.1700
Data Index: 4682124 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5773. Min Range: -5.5773
Max Act: 5.4211. Min Act: -0.1700
Data Index: 6934571 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5773. Min Range: -5.5773
Max Act: 5.3898. Min Act: -0.1700
Data Index: 909923 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5773. Min Range: -5.5773
Max Act: 5.3898. Min Act: -0.1700
Data Index: 4335743 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5773. Min Range: -5.5773
Max Act: 5.3898. Min Act: -0.1700
Data Index: 5948936 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5773. Min Range: -5.5773
Max Act: 5.3586. Min Act: -0.1700
Data Index: 54600 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5773. Min Range: -5.5773
Max Act: 5.3586. Min Act: -0.1700
Data Index: 3349631 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5773. Min Range: -5.5773
Max Act: 5.3586. Min Act: -0.1700
Data Index: 7860839 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5773. Min Range: -5.5773
Max Act: 5.3273. Min Act: -0.1700
Data Index: 5212286 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5773. Min Range: -5.5773
Max Act: 5.3273. Min Act: -0.1700
Data Index: 7697476 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5773. Min Range: -5.5773
Max Act: 5.2961. Min Act: -0.1700
Data Index: 3443763 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5773. Min Range: -5.5773
Max Act: 5.2961. Min Act: -0.1700
Data Index: 5116627 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5773. Min Range: -5.5773
Max Act: 5.2961. Min Act: -0.1700
Data Index: 677700 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5773. Min Range: -5.5773
Max Act: 5.2961. Min Act: -0.1700
Data Index: 5513482 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #19