Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2841 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0115. Min Range: -7.0115
Max Act: 7.0115. Min Act: -0.1700
Data Index: 5465047 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0115. Min Range: -7.0115
Max Act: 7.0115. Min Act: -0.1700
Data Index: 129926 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0115. Min Range: -7.0115
Max Act: 6.9490. Min Act: -0.1700
Data Index: 7537332 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0115. Min Range: -7.0115
Max Act: 6.8552. Min Act: -0.1700
Data Index: 8002504 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0115. Min Range: -7.0115
Max Act: 6.8240. Min Act: -0.1700
Data Index: 8417383 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0115. Min Range: -7.0115
Max Act: 6.8240. Min Act: -0.1700
Data Index: 6208964 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0115. Min Range: -7.0115
Max Act: 6.7615. Min Act: -0.1700
Data Index: 1924420 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0115. Min Range: -7.0115
Max Act: 6.6990. Min Act: -0.1700
Data Index: 1939766 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0115. Min Range: -7.0115
Max Act: 6.6677. Min Act: -0.1700
Data Index: 5484026 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0115. Min Range: -7.0115
Max Act: 6.6990. Min Act: -0.1700
Data Index: 3102180 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0115. Min Range: -7.0115
Max Act: 6.5740. Min Act: -0.1700
Data Index: 785023 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0115. Min Range: -7.0115
Max Act: 6.5427. Min Act: -0.1700
Data Index: 7191110 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0115. Min Range: -7.0115
Max Act: 6.5115. Min Act: -0.1700
Data Index: 671098 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0115. Min Range: -7.0115
Max Act: 6.5427. Min Act: -0.1700
Data Index: 1488798 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0115. Min Range: -7.0115
Max Act: 6.5427. Min Act: -0.1700
Data Index: 2488159 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0115. Min Range: -7.0115
Max Act: 6.5115. Min Act: -0.1700
Data Index: 8002499 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0115. Min Range: -7.0115
Max Act: 6.5115. Min Act: -0.1700
Data Index: 243011 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0115. Min Range: -7.0115
Max Act: 6.5115. Min Act: -0.1700
Data Index: 7495830 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0115. Min Range: -7.0115
Max Act: 6.5115. Min Act: -0.1700
Data Index: 3554214 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0115. Min Range: -7.0115
Max Act: 6.5115. Min Act: -0.1700
Data Index: 1498406 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #19