Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1939 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2788. Min Range: -4.2788
Max Act: 4.2788. Min Act: -0.1700
Data Index: 2400451 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2788. Min Range: -4.2788
Max Act: 4.1851. Min Act: -0.1700
Data Index: 5485046 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2788. Min Range: -4.2788
Max Act: 4.1851. Min Act: -0.1700
Data Index: 4195429 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2788. Min Range: -4.2788
Max Act: 4.1538. Min Act: -0.1700
Data Index: 8121720 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2788. Min Range: -4.2788
Max Act: 4.0600. Min Act: -0.1700
Data Index: 7221870 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2788. Min Range: -4.2788
Max Act: 4.0913. Min Act: -0.1700
Data Index: 6422750 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2788. Min Range: -4.2788
Max Act: 4.0600. Min Act: -0.1700
Data Index: 5997028 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2788. Min Range: -4.2788
Max Act: 4.0288. Min Act: -0.1700
Data Index: 8121722 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2788. Min Range: -4.2788
Max Act: 4.0288. Min Act: -0.1700
Data Index: 7048393 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2788. Min Range: -4.2788
Max Act: 3.9975. Min Act: -0.1700
Data Index: 393664 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2788. Min Range: -4.2788
Max Act: 3.9975. Min Act: -0.1700
Data Index: 6461205 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2788. Min Range: -4.2788
Max Act: 4.0288. Min Act: -0.1700
Data Index: 8311116 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2788. Min Range: -4.2788
Max Act: 3.9975. Min Act: -0.1700
Data Index: 2758815 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2788. Min Range: -4.2788
Max Act: 3.9975. Min Act: -0.1700
Data Index: 4732878 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2788. Min Range: -4.2788
Max Act: 3.9975. Min Act: -0.1700
Data Index: 309619 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2788. Min Range: -4.2788
Max Act: 3.9663. Min Act: -0.1700
Data Index: 7585702 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2788. Min Range: -4.2788
Max Act: 3.9975. Min Act: -0.1700
Data Index: 8186432 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2788. Min Range: -4.2788
Max Act: 3.9975. Min Act: -0.1700
Data Index: 532751 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2788. Min Range: -4.2788
Max Act: 3.9663. Min Act: -0.1700
Data Index: 6873532 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2788. Min Range: -4.2788
Max Act: 3.9663. Min Act: -0.1700
Data Index: 4548173 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #19