Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6349 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1822. Min Range: -7.1822
Max Act: 7.1822. Min Act: -0.1700
Data Index: 905971 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1822. Min Range: -7.1822
Max Act: 7.1510. Min Act: -0.1700
Data Index: 7223819 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1822. Min Range: -7.1822
Max Act: 7.1510. Min Act: -0.1700
Data Index: 4208097 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1822. Min Range: -7.1822
Max Act: 7.1197. Min Act: -0.1700
Data Index: 6194383 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1822. Min Range: -7.1822
Max Act: 7.1197. Min Act: -0.1700
Data Index: 671890 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1822. Min Range: -7.1822
Max Act: 7.1197. Min Act: -0.1700
Data Index: 131792 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1822. Min Range: -7.1822
Max Act: 7.0260. Min Act: -0.1700
Data Index: 471738 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1822. Min Range: -7.1822
Max Act: 6.9635. Min Act: -0.1700
Data Index: 8521872 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1822. Min Range: -7.1822
Max Act: 6.9635. Min Act: -0.1700
Data Index: 6400488 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1822. Min Range: -7.1822
Max Act: 6.9010. Min Act: -0.1700
Data Index: 8249130 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1822. Min Range: -7.1822
Max Act: 6.9322. Min Act: -0.1700
Data Index: 2876381 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1822. Min Range: -7.1822
Max Act: 6.9322. Min Act: -0.1700
Data Index: 5536317 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1822. Min Range: -7.1822
Max Act: 6.9010. Min Act: -0.1700
Data Index: 4249439 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1822. Min Range: -7.1822
Max Act: 6.9010. Min Act: -0.1700
Data Index: 202349 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1822. Min Range: -7.1822
Max Act: 6.8697. Min Act: -0.1700
Data Index: 3285486 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1822. Min Range: -7.1822
Max Act: 6.8697. Min Act: -0.1700
Data Index: 6018540 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1822. Min Range: -7.1822
Max Act: 6.8697. Min Act: -0.1700
Data Index: 1780914 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1822. Min Range: -7.1822
Max Act: 6.8385. Min Act: -0.1700
Data Index: 2796962 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1822. Min Range: -7.1822
Max Act: 6.7760. Min Act: -0.1700
Data Index: 1806329 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1822. Min Range: -7.1822
Max Act: 6.8072. Min Act: -0.1700
Data Index: 1769972 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #19