Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1547 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7555. Min Range: -6.7555
Max Act: 6.7555. Min Act: -0.1700
Data Index: 5890593 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7555. Min Range: -6.7555
Max Act: 6.6305. Min Act: -0.1700
Data Index: 8828965 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7555. Min Range: -6.7555
Max Act: 6.4430. Min Act: -0.1700
Data Index: 8366068 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7555. Min Range: -6.7555
Max Act: 6.4430. Min Act: -0.1700
Data Index: 5534619 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7555. Min Range: -6.7555
Max Act: 6.3805. Min Act: -0.1700
Data Index: 360750 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7555. Min Range: -6.7555
Max Act: 6.3805. Min Act: -0.1700
Data Index: 4846506 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7555. Min Range: -6.7555
Max Act: 6.3492. Min Act: -0.1700
Data Index: 3407217 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7555. Min Range: -6.7555
Max Act: 6.3492. Min Act: -0.1700
Data Index: 8742312 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7555. Min Range: -6.7555
Max Act: 6.3492. Min Act: -0.1700
Data Index: 8131435 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7555. Min Range: -6.7555
Max Act: 6.2867. Min Act: -0.1700
Data Index: 533651 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7555. Min Range: -6.7555
Max Act: 6.2867. Min Act: -0.1700
Data Index: 5065573 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7555. Min Range: -6.7555
Max Act: 6.2867. Min Act: -0.1700
Data Index: 4134005 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7555. Min Range: -6.7555
Max Act: 6.2555. Min Act: -0.1700
Data Index: 6216236 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7555. Min Range: -6.7555
Max Act: 6.2555. Min Act: -0.1700
Data Index: 354358 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7555. Min Range: -6.7555
Max Act: 6.2867. Min Act: -0.1700
Data Index: 2895035 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7555. Min Range: -6.7555
Max Act: 6.2242. Min Act: -0.1700
Data Index: 6026832 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7555. Min Range: -6.7555
Max Act: 6.2242. Min Act: -0.1700
Data Index: 8822099 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7555. Min Range: -6.7555
Max Act: 6.2242. Min Act: -0.1700
Data Index: 1174853 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7555. Min Range: -6.7555
Max Act: 6.1930. Min Act: -0.1700
Data Index: 6519434 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7555. Min Range: -6.7555
Max Act: 6.1930. Min Act: -0.1700
Data Index: 3328907 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #19