Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3219 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8652. Min Range: -4.8652
Max Act: 4.8652. Min Act: -0.1700
Data Index: 494005 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8652. Min Range: -4.8652
Max Act: 4.8652. Min Act: -0.1700
Data Index: 7560730 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8652. Min Range: -4.8652
Max Act: 4.8339. Min Act: -0.1700
Data Index: 803244 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8652. Min Range: -4.8652
Max Act: 4.8027. Min Act: -0.1700
Data Index: 2882134 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8652. Min Range: -4.8652
Max Act: 4.7714. Min Act: -0.1700
Data Index: 5816145 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8652. Min Range: -4.8652
Max Act: 4.7402. Min Act: -0.1700
Data Index: 2726962 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8652. Min Range: -4.8652
Max Act: 4.7089. Min Act: -0.1700
Data Index: 7779189 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8652. Min Range: -4.8652
Max Act: 4.7402. Min Act: -0.1700
Data Index: 7296606 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8652. Min Range: -4.8652
Max Act: 4.7402. Min Act: -0.1700
Data Index: 3557452 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8652. Min Range: -4.8652
Max Act: 4.7089. Min Act: -0.1700
Data Index: 1805928 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8652. Min Range: -4.8652
Max Act: 4.6777. Min Act: -0.1700
Data Index: 715085 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8652. Min Range: -4.8652
Max Act: 4.7089. Min Act: -0.1700
Data Index: 8724387 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8652. Min Range: -4.8652
Max Act: 4.6777. Min Act: -0.1700
Data Index: 7560728 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8652. Min Range: -4.8652
Max Act: 4.7089. Min Act: -0.1700
Data Index: 3319164 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8652. Min Range: -4.8652
Max Act: 4.7089. Min Act: -0.1700
Data Index: 2379045 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8652. Min Range: -4.8652
Max Act: 4.7089. Min Act: -0.1700
Data Index: 829044 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8652. Min Range: -4.8652
Max Act: 4.7089. Min Act: -0.1700
Data Index: 6258498 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8652. Min Range: -4.8652
Max Act: 4.6777. Min Act: -0.1700
Data Index: 3688977 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8652. Min Range: -4.8652
Max Act: 4.6777. Min Act: -0.1700
Data Index: 7740905 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8652. Min Range: -4.8652
Max Act: 4.6777. Min Act: -0.1700
Data Index: 572673 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #19