Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4733 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6654. Min Range: -8.6654
Max Act: 8.6654. Min Act: -0.1700
Data Index: 3487117 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6654. Min Range: -8.6654
Max Act: 8.6029. Min Act: -0.1700
Data Index: 6353578 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6654. Min Range: -8.6654
Max Act: 8.3529. Min Act: -0.1700
Data Index: 2563249 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6654. Min Range: -8.6654
Max Act: 8.3529. Min Act: -0.1700
Data Index: 5512481 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6654. Min Range: -8.6654
Max Act: 8.2904. Min Act: -0.1700
Data Index: 2953228 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6654. Min Range: -8.6654
Max Act: 8.2904. Min Act: -0.1700
Data Index: 4128837 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6654. Min Range: -8.6654
Max Act: 8.2904. Min Act: -0.1700
Data Index: 4179909 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6654. Min Range: -8.6654
Max Act: 8.1654. Min Act: -0.1700
Data Index: 3349088 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6654. Min Range: -8.6654
Max Act: 8.1654. Min Act: -0.1700
Data Index: 2422980 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6654. Min Range: -8.6654
Max Act: 8.1654. Min Act: -0.1700
Data Index: 2086895 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6654. Min Range: -8.6654
Max Act: 8.1654. Min Act: -0.1700
Data Index: 6251570 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6654. Min Range: -8.6654
Max Act: 8.1654. Min Act: -0.1700
Data Index: 6624798 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6654. Min Range: -8.6654
Max Act: 8.1029. Min Act: -0.1700
Data Index: 6672915 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6654. Min Range: -8.6654
Max Act: 8.1029. Min Act: -0.1700
Data Index: 4199103 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6654. Min Range: -8.6654
Max Act: 8.1029. Min Act: -0.1700
Data Index: 1175963 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6654. Min Range: -8.6654
Max Act: 8.0404. Min Act: -0.1700
Data Index: 4063656 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6654. Min Range: -8.6654
Max Act: 8.0404. Min Act: -0.1700
Data Index: 1070110 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6654. Min Range: -8.6654
Max Act: 8.0404. Min Act: -0.1700
Data Index: 7477646 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6654. Min Range: -8.6654
Max Act: 8.0404. Min Act: -0.1700
Data Index: 5645936 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6654. Min Range: -8.6654
Max Act: 7.9779. Min Act: -0.1700
Data Index: 3433557 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #19