Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3720 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3934. Min Range: -4.3934
Max Act: 4.3934. Min Act: -0.1700
Data Index: 5869888 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3934. Min Range: -4.3934
Max Act: 4.3621. Min Act: -0.1700
Data Index: 3261233 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3934. Min Range: -4.3934
Max Act: 4.2996. Min Act: -0.1700
Data Index: 6500345 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3934. Min Range: -4.3934
Max Act: 4.2684. Min Act: -0.1700
Data Index: 5251872 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3934. Min Range: -4.3934
Max Act: 4.2371. Min Act: -0.1700
Data Index: 2818396 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3934. Min Range: -4.3934
Max Act: 4.2059. Min Act: -0.1700
Data Index: 742967 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3934. Min Range: -4.3934
Max Act: 4.1746. Min Act: -0.1700
Data Index: 3390631 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3934. Min Range: -4.3934
Max Act: 4.1434. Min Act: -0.1700
Data Index: 3999333 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3934. Min Range: -4.3934
Max Act: 4.0809. Min Act: -0.1700
Data Index: 2983805 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3934. Min Range: -4.3934
Max Act: 4.0809. Min Act: -0.1700
Data Index: 1880804 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3934. Min Range: -4.3934
Max Act: 4.0809. Min Act: -0.1700
Data Index: 3685949 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3934. Min Range: -4.3934
Max Act: 4.0496. Min Act: -0.1700
Data Index: 34221 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3934. Min Range: -4.3934
Max Act: 4.0496. Min Act: -0.1700
Data Index: 3659270 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3934. Min Range: -4.3934
Max Act: 4.0496. Min Act: -0.1700
Data Index: 2260479 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3934. Min Range: -4.3934
Max Act: 4.0809. Min Act: -0.1700
Data Index: 3324983 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3934. Min Range: -4.3934
Max Act: 4.0496. Min Act: -0.1700
Data Index: 8178076 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3934. Min Range: -4.3934
Max Act: 4.0496. Min Act: -0.1700
Data Index: 2152336 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3934. Min Range: -4.3934
Max Act: 4.0183. Min Act: -0.1700
Data Index: 4346952 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3934. Min Range: -4.3934
Max Act: 4.0183. Min Act: -0.1700
Data Index: 3624345 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3934. Min Range: -4.3934
Max Act: 4.0183. Min Act: -0.1700
Data Index: 2501194 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #19