Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1613 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.3119. Min Range: -9.3119
Max Act: 9.3119. Min Act: -0.1700
Data Index: 5027459 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3119. Min Range: -9.3119
Max Act: 9.3119. Min Act: -0.1700
Data Index: 5524765 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3119. Min Range: -9.3119
Max Act: 9.1244. Min Act: -0.1700
Data Index: 7247811 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3119. Min Range: -9.3119
Max Act: 9.0619. Min Act: -0.1700
Data Index: 1058538 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3119. Min Range: -9.3119
Max Act: 9.1244. Min Act: -0.1700
Data Index: 7548146 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3119. Min Range: -9.3119
Max Act: 9.0619. Min Act: -0.1700
Data Index: 5580007 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3119. Min Range: -9.3119
Max Act: 9.1244. Min Act: -0.1700
Data Index: 1058539 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3119. Min Range: -9.3119
Max Act: 9.1244. Min Act: -0.1700
Data Index: 5849047 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3119. Min Range: -9.3119
Max Act: 9.0619. Min Act: -0.1700
Data Index: 1252965 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3119. Min Range: -9.3119
Max Act: 9.0619. Min Act: -0.1700
Data Index: 4229455 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3119. Min Range: -9.3119
Max Act: 9.0619. Min Act: -0.1700
Data Index: 7969568 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3119. Min Range: -9.3119
Max Act: 9.0619. Min Act: -0.1700
Data Index: 4298836 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3119. Min Range: -9.3119
Max Act: 8.9994. Min Act: -0.1700
Data Index: 8259582 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3119. Min Range: -9.3119
Max Act: 9.0619. Min Act: -0.1700
Data Index: 5915829 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3119. Min Range: -9.3119
Max Act: 8.9994. Min Act: -0.1700
Data Index: 880097 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3119. Min Range: -9.3119
Max Act: 9.0619. Min Act: -0.1700
Data Index: 2109381 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3119. Min Range: -9.3119
Max Act: 8.9369. Min Act: -0.1700
Data Index: 282643 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3119. Min Range: -9.3119
Max Act: 8.9994. Min Act: -0.1700
Data Index: 2690494 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3119. Min Range: -9.3119
Max Act: 8.9369. Min Act: -0.1700
Data Index: 26900 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3119. Min Range: -9.3119
Max Act: 8.8744. Min Act: -0.1700
Data Index: 871286 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #19