Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4807 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2894. Min Range: -5.2894
Max Act: 5.2894. Min Act: -0.1700
Data Index: 733933 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2894. Min Range: -5.2894
Max Act: 5.1957. Min Act: -0.1700
Data Index: 531971 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2894. Min Range: -5.2894
Max Act: 5.1332. Min Act: -0.1700
Data Index: 5743424 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2894. Min Range: -5.2894
Max Act: 5.1019. Min Act: -0.1700
Data Index: 8563520 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2894. Min Range: -5.2894
Max Act: 5.1019. Min Act: -0.1700
Data Index: 7789008 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2894. Min Range: -5.2894
Max Act: 5.1019. Min Act: -0.1700
Data Index: 5663698 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2894. Min Range: -5.2894
Max Act: 5.0082. Min Act: -0.1700
Data Index: 8074172 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2894. Min Range: -5.2894
Max Act: 4.9769. Min Act: -0.1700
Data Index: 331317 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2894. Min Range: -5.2894
Max Act: 4.9769. Min Act: -0.1700
Data Index: 4700517 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2894. Min Range: -5.2894
Max Act: 4.9457. Min Act: -0.1700
Data Index: 8688425 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2894. Min Range: -5.2894
Max Act: 4.9457. Min Act: -0.1700
Data Index: 1542128 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2894. Min Range: -5.2894
Max Act: 4.8832. Min Act: -0.1700
Data Index: 6627638 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2894. Min Range: -5.2894
Max Act: 4.9144. Min Act: -0.1700
Data Index: 6945450 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2894. Min Range: -5.2894
Max Act: 4.8832. Min Act: -0.1700
Data Index: 4857897 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2894. Min Range: -5.2894
Max Act: 4.8832. Min Act: -0.1700
Data Index: 3639220 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2894. Min Range: -5.2894
Max Act: 4.8519. Min Act: -0.1700
Data Index: 8028963 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2894. Min Range: -5.2894
Max Act: 4.8519. Min Act: -0.1700
Data Index: 1904049 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2894. Min Range: -5.2894
Max Act: 4.8519. Min Act: -0.1700
Data Index: 7035177 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2894. Min Range: -5.2894
Max Act: 4.8519. Min Act: -0.1700
Data Index: 6483814 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2894. Min Range: -5.2894
Max Act: 4.8519. Min Act: -0.1700
Data Index: 246438 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #19