Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4856 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7967. Min Range: -6.7967
Max Act: 6.7967. Min Act: -0.1700
Data Index: 6568596 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7967. Min Range: -6.7967
Max Act: 6.6404. Min Act: -0.1700
Data Index: 6109643 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7967. Min Range: -6.7967
Max Act: 6.4217. Min Act: -0.1700
Data Index: 5749987 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7967. Min Range: -6.7967
Max Act: 6.3904. Min Act: -0.1700
Data Index: 1001892 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7967. Min Range: -6.7967
Max Act: 6.3904. Min Act: -0.1700
Data Index: 2065714 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7967. Min Range: -6.7967
Max Act: 6.3592. Min Act: -0.1700
Data Index: 5353629 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7967. Min Range: -6.7967
Max Act: 6.2967. Min Act: -0.1700
Data Index: 2563464 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7967. Min Range: -6.7967
Max Act: 6.2967. Min Act: -0.1700
Data Index: 7935705 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7967. Min Range: -6.7967
Max Act: 6.2654. Min Act: -0.1700
Data Index: 6003156 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7967. Min Range: -6.7967
Max Act: 6.2654. Min Act: -0.1700
Data Index: 6544150 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7967. Min Range: -6.7967
Max Act: 6.2342. Min Act: -0.1700
Data Index: 2035355 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7967. Min Range: -6.7967
Max Act: 6.2342. Min Act: -0.1700
Data Index: 88780 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7967. Min Range: -6.7967
Max Act: 6.1717. Min Act: -0.1700
Data Index: 2759918 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7967. Min Range: -6.7967
Max Act: 6.1404. Min Act: -0.1700
Data Index: 5455751 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7967. Min Range: -6.7967
Max Act: 6.1717. Min Act: -0.1700
Data Index: 8515889 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7967. Min Range: -6.7967
Max Act: 6.1404. Min Act: -0.1700
Data Index: 1707223 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7967. Min Range: -6.7967
Max Act: 6.1404. Min Act: -0.1700
Data Index: 8081729 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7967. Min Range: -6.7967
Max Act: 6.1092. Min Act: -0.1700
Data Index: 4743090 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7967. Min Range: -6.7967
Max Act: 6.1092. Min Act: -0.1700
Data Index: 5449075 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7967. Min Range: -6.7967
Max Act: 6.1092. Min Act: -0.1700
Data Index: 7603029 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #19