Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 22 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1285. Min Range: -4.1285
Max Act: 4.1285. Min Act: -0.1700
Data Index: 7346637 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1285. Min Range: -4.1285
Max Act: 3.9097. Min Act: -0.1700
Data Index: 7951850 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1285. Min Range: -4.1285
Max Act: 3.9410. Min Act: -0.1700
Data Index: 8028300 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1285. Min Range: -4.1285
Max Act: 3.8784. Min Act: -0.1700
Data Index: 8782547 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1285. Min Range: -4.1285
Max Act: 3.8159. Min Act: -0.1700
Data Index: 222648 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1285. Min Range: -4.1285
Max Act: 3.7534. Min Act: -0.1700
Data Index: 8372113 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1285. Min Range: -4.1285
Max Act: 3.8159. Min Act: -0.1700
Data Index: 5077860 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1285. Min Range: -4.1285
Max Act: 3.7846. Min Act: -0.1700
Data Index: 4280995 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1285. Min Range: -4.1285
Max Act: 3.7846. Min Act: -0.1700
Data Index: 6747356 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1285. Min Range: -4.1285
Max Act: 3.7846. Min Act: -0.1700
Data Index: 1730942 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1285. Min Range: -4.1285
Max Act: 3.7846. Min Act: -0.1700
Data Index: 2395658 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1285. Min Range: -4.1285
Max Act: 3.7534. Min Act: -0.1700
Data Index: 2402446 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1285. Min Range: -4.1285
Max Act: 3.7377. Min Act: -0.1700
Data Index: 2420587 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1285. Min Range: -4.1285
Max Act: 3.7221. Min Act: -0.1700
Data Index: 5337888 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1285. Min Range: -4.1285
Max Act: 3.7064. Min Act: -0.1700
Data Index: 2013478 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1285. Min Range: -4.1285
Max Act: 3.7064. Min Act: -0.1700
Data Index: 7504472 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1285. Min Range: -4.1285
Max Act: 3.7221. Min Act: -0.1700
Data Index: 5227140 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1285. Min Range: -4.1285
Max Act: 3.7064. Min Act: -0.1700
Data Index: 7075817 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1285. Min Range: -4.1285
Max Act: 3.6908. Min Act: -0.1700
Data Index: 7308954 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1285. Min Range: -4.1285
Max Act: 3.7064. Min Act: -0.1700
Data Index: 7694058 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #19