Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3584 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9869. Min Range: -5.9869
Max Act: 5.9869. Min Act: -0.1700
Data Index: 5388212 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9869. Min Range: -5.9869
Max Act: 5.8931. Min Act: -0.1700
Data Index: 2257206 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9869. Min Range: -5.9869
Max Act: 5.8306. Min Act: -0.1700
Data Index: 3771885 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9869. Min Range: -5.9869
Max Act: 5.7994. Min Act: -0.1700
Data Index: 7213305 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9869. Min Range: -5.9869
Max Act: 5.7369. Min Act: -0.1700
Data Index: 2419670 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9869. Min Range: -5.9869
Max Act: 5.7056. Min Act: -0.1700
Data Index: 6809566 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9869. Min Range: -5.9869
Max Act: 5.6744. Min Act: -0.1700
Data Index: 7140082 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9869. Min Range: -5.9869
Max Act: 5.7056. Min Act: -0.1700
Data Index: 7752176 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9869. Min Range: -5.9869
Max Act: 5.6744. Min Act: -0.1700
Data Index: 5443490 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9869. Min Range: -5.9869
Max Act: 5.6431. Min Act: -0.1700
Data Index: 1641775 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9869. Min Range: -5.9869
Max Act: 5.6431. Min Act: -0.1700
Data Index: 7329979 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9869. Min Range: -5.9869
Max Act: 5.6431. Min Act: -0.1700
Data Index: 2791588 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9869. Min Range: -5.9869
Max Act: 5.6431. Min Act: -0.1700
Data Index: 3193005 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9869. Min Range: -5.9869
Max Act: 5.6119. Min Act: -0.1700
Data Index: 8407881 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9869. Min Range: -5.9869
Max Act: 5.6119. Min Act: -0.1700
Data Index: 6327670 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9869. Min Range: -5.9869
Max Act: 5.6119. Min Act: -0.1700
Data Index: 28436 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9869. Min Range: -5.9869
Max Act: 5.6119. Min Act: -0.1700
Data Index: 1182415 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9869. Min Range: -5.9869
Max Act: 5.5806. Min Act: -0.1700
Data Index: 3989698 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9869. Min Range: -5.9869
Max Act: 5.5806. Min Act: -0.1700
Data Index: 2739441 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9869. Min Range: -5.9869
Max Act: 5.5806. Min Act: -0.1700
Data Index: 5102980 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #19