Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 50 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3403. Min Range: -4.3403
Max Act: 4.3403. Min Act: -0.1700
Data Index: 385969 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3403. Min Range: -4.3403
Max Act: 4.3090. Min Act: -0.1700
Data Index: 3698022 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3403. Min Range: -4.3403
Max Act: 4.2153. Min Act: -0.1700
Data Index: 7151999 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3403. Min Range: -4.3403
Max Act: 4.2153. Min Act: -0.1700
Data Index: 7996639 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3403. Min Range: -4.3403
Max Act: 4.2153. Min Act: -0.1700
Data Index: 6214473 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3403. Min Range: -4.3403
Max Act: 4.1840. Min Act: -0.1700
Data Index: 1603873 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3403. Min Range: -4.3403
Max Act: 4.2153. Min Act: -0.1700
Data Index: 2369720 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3403. Min Range: -4.3403
Max Act: 4.1528. Min Act: -0.1700
Data Index: 3233971 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3403. Min Range: -4.3403
Max Act: 4.1528. Min Act: -0.1700
Data Index: 680436 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3403. Min Range: -4.3403
Max Act: 4.1528. Min Act: -0.1700
Data Index: 49915 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3403. Min Range: -4.3403
Max Act: 4.1528. Min Act: -0.1700
Data Index: 6714325 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3403. Min Range: -4.3403
Max Act: 4.1215. Min Act: -0.1700
Data Index: 2042647 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3403. Min Range: -4.3403
Max Act: 4.1215. Min Act: -0.1700
Data Index: 3689907 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3403. Min Range: -4.3403
Max Act: 4.1215. Min Act: -0.1700
Data Index: 4782603 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3403. Min Range: -4.3403
Max Act: 4.0903. Min Act: -0.1700
Data Index: 1737545 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3403. Min Range: -4.3403
Max Act: 4.0903. Min Act: -0.1700
Data Index: 1470047 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3403. Min Range: -4.3403
Max Act: 4.0590. Min Act: -0.1700
Data Index: 4711363 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3403. Min Range: -4.3403
Max Act: 4.0590. Min Act: -0.1700
Data Index: 1656023 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3403. Min Range: -4.3403
Max Act: 4.0590. Min Act: -0.1700
Data Index: 4782401 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3403. Min Range: -4.3403
Max Act: 4.0590. Min Act: -0.1700
Data Index: 4010112 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #19