Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 987 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0590. Min Range: -7.0590
Max Act: 7.0590. Min Act: -0.1700
Data Index: 1647271 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0590. Min Range: -7.0590
Max Act: 7.0278. Min Act: -0.1700
Data Index: 601903 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0590. Min Range: -7.0590
Max Act: 6.8090. Min Act: -0.1700
Data Index: 4670160 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0590. Min Range: -7.0590
Max Act: 6.6840. Min Act: -0.1700
Data Index: 7614677 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0590. Min Range: -7.0590
Max Act: 6.7153. Min Act: -0.1700
Data Index: 1826197 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0590. Min Range: -7.0590
Max Act: 6.6528. Min Act: -0.1700
Data Index: 8267519 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0590. Min Range: -7.0590
Max Act: 6.6840. Min Act: -0.1700
Data Index: 5708501 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0590. Min Range: -7.0590
Max Act: 6.6215. Min Act: -0.1700
Data Index: 1419995 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0590. Min Range: -7.0590
Max Act: 6.5278. Min Act: -0.1700
Data Index: 2904289 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0590. Min Range: -7.0590
Max Act: 6.4965. Min Act: -0.1700
Data Index: 6367891 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0590. Min Range: -7.0590
Max Act: 6.4965. Min Act: -0.1700
Data Index: 1833978 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0590. Min Range: -7.0590
Max Act: 6.4965. Min Act: -0.1700
Data Index: 5039896 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0590. Min Range: -7.0590
Max Act: 6.4653. Min Act: -0.1700
Data Index: 2670565 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0590. Min Range: -7.0590
Max Act: 6.4653. Min Act: -0.1700
Data Index: 5199323 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0590. Min Range: -7.0590
Max Act: 6.4340. Min Act: -0.1700
Data Index: 2636502 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0590. Min Range: -7.0590
Max Act: 6.4340. Min Act: -0.1700
Data Index: 431725 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0590. Min Range: -7.0590
Max Act: 6.4340. Min Act: -0.1700
Data Index: 527734 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0590. Min Range: -7.0590
Max Act: 6.4340. Min Act: -0.1700
Data Index: 4190032 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0590. Min Range: -7.0590
Max Act: 6.4028. Min Act: -0.1700
Data Index: 4616241 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0590. Min Range: -7.0590
Max Act: 6.4028. Min Act: -0.1700
Data Index: 5625622 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #19