Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3537 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4556. Min Range: -8.4556
Max Act: 8.4556. Min Act: -0.1700
Data Index: 1537244 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4556. Min Range: -8.4556
Max Act: 8.4556. Min Act: -0.1700
Data Index: 5205740 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4556. Min Range: -8.4556
Max Act: 8.2056. Min Act: -0.1700
Data Index: 5856005 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4556. Min Range: -8.4556
Max Act: 8.0806. Min Act: -0.1700
Data Index: 5402747 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4556. Min Range: -8.4556
Max Act: 8.0181. Min Act: -0.1700
Data Index: 1017092 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4556. Min Range: -8.4556
Max Act: 8.0181. Min Act: -0.1700
Data Index: 3607211 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4556. Min Range: -8.4556
Max Act: 7.9556. Min Act: -0.1700
Data Index: 4522584 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4556. Min Range: -8.4556
Max Act: 7.8931. Min Act: -0.1700
Data Index: 5477282 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4556. Min Range: -8.4556
Max Act: 7.8931. Min Act: -0.1700
Data Index: 7703984 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4556. Min Range: -8.4556
Max Act: 7.8931. Min Act: -0.1700
Data Index: 3695019 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4556. Min Range: -8.4556
Max Act: 7.8931. Min Act: -0.1700
Data Index: 6520380 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4556. Min Range: -8.4556
Max Act: 7.8931. Min Act: -0.1700
Data Index: 2546772 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4556. Min Range: -8.4556
Max Act: 7.8306. Min Act: -0.1700
Data Index: 6812722 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4556. Min Range: -8.4556
Max Act: 7.8306. Min Act: -0.1700
Data Index: 5629438 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4556. Min Range: -8.4556
Max Act: 7.8306. Min Act: -0.1700
Data Index: 2055230 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4556. Min Range: -8.4556
Max Act: 7.8306. Min Act: -0.1700
Data Index: 4709226 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4556. Min Range: -8.4556
Max Act: 7.8306. Min Act: -0.1700
Data Index: 415428 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4556. Min Range: -8.4556
Max Act: 7.8306. Min Act: -0.1700
Data Index: 3328252 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4556. Min Range: -8.4556
Max Act: 7.8306. Min Act: -0.1700
Data Index: 1749570 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4556. Min Range: -8.4556
Max Act: 7.8306. Min Act: -0.1700
Data Index: 1030620 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #19