Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3956 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3535. Min Range: -5.3535
Max Act: 5.3535. Min Act: -0.1700
Data Index: 762936 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3535. Min Range: -5.3535
Max Act: 5.1347. Min Act: -0.1700
Data Index: 7953418 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3535. Min Range: -5.3535
Max Act: 4.8847. Min Act: -0.1700
Data Index: 8566867 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3535. Min Range: -5.3535
Max Act: 4.8535. Min Act: -0.1700
Data Index: 2544774 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3535. Min Range: -5.3535
Max Act: 4.8222. Min Act: -0.1700
Data Index: 2055663 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3535. Min Range: -5.3535
Max Act: 4.6972. Min Act: -0.1700
Data Index: 8406626 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3535. Min Range: -5.3535
Max Act: 4.6972. Min Act: -0.1700
Data Index: 1663229 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3535. Min Range: -5.3535
Max Act: 4.6972. Min Act: -0.1700
Data Index: 1962736 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3535. Min Range: -5.3535
Max Act: 4.6347. Min Act: -0.1700
Data Index: 3618576 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3535. Min Range: -5.3535
Max Act: 4.6347. Min Act: -0.1700
Data Index: 6511733 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3535. Min Range: -5.3535
Max Act: 4.6035. Min Act: -0.1700
Data Index: 5989009 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3535. Min Range: -5.3535
Max Act: 4.5722. Min Act: -0.1700
Data Index: 8774445 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3535. Min Range: -5.3535
Max Act: 4.6035. Min Act: -0.1700
Data Index: 6491854 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3535. Min Range: -5.3535
Max Act: 4.5722. Min Act: -0.1700
Data Index: 1927121 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3535. Min Range: -5.3535
Max Act: 4.5722. Min Act: -0.1700
Data Index: 7632481 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3535. Min Range: -5.3535
Max Act: 4.5722. Min Act: -0.1700
Data Index: 5789535 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3535. Min Range: -5.3535
Max Act: 4.5410. Min Act: -0.1700
Data Index: 6217569 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3535. Min Range: -5.3535
Max Act: 4.5410. Min Act: -0.1700
Data Index: 2983526 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3535. Min Range: -5.3535
Max Act: 4.5410. Min Act: -0.1700
Data Index: 4976888 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3535. Min Range: -5.3535
Max Act: 4.5410. Min Act: -0.1700
Data Index: 5060697 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #19