Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5134 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2097. Min Range: -4.2097
Max Act: 4.2097. Min Act: -0.1700
Data Index: 3934276 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2097. Min Range: -4.2097
Max Act: 4.0534. Min Act: -0.1700
Data Index: 6316934 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2097. Min Range: -4.2097
Max Act: 3.9909. Min Act: -0.1700
Data Index: 3224789 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2097. Min Range: -4.2097
Max Act: 3.9596. Min Act: -0.1700
Data Index: 768920 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2097. Min Range: -4.2097
Max Act: 3.8971. Min Act: -0.1700
Data Index: 3048271 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2097. Min Range: -4.2097
Max Act: 3.8658. Min Act: -0.1700
Data Index: 2267500 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2097. Min Range: -4.2097
Max Act: 3.8189. Min Act: -0.1700
Data Index: 4311688 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2097. Min Range: -4.2097
Max Act: 3.8345. Min Act: -0.1700
Data Index: 667023 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2097. Min Range: -4.2097
Max Act: 3.8189. Min Act: -0.1700
Data Index: 3993433 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2097. Min Range: -4.2097
Max Act: 3.8033. Min Act: -0.1700
Data Index: 3732152 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2097. Min Range: -4.2097
Max Act: 3.7876. Min Act: -0.1700
Data Index: 378866 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2097. Min Range: -4.2097
Max Act: 3.7876. Min Act: -0.1700
Data Index: 2757846 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2097. Min Range: -4.2097
Max Act: 3.7876. Min Act: -0.1700
Data Index: 6504772 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2097. Min Range: -4.2097
Max Act: 3.7876. Min Act: -0.1700
Data Index: 8776310 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2097. Min Range: -4.2097
Max Act: 3.7876. Min Act: -0.1700
Data Index: 2376776 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2097. Min Range: -4.2097
Max Act: 3.7720. Min Act: -0.1700
Data Index: 3286713 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2097. Min Range: -4.2097
Max Act: 3.7720. Min Act: -0.1700
Data Index: 45576 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2097. Min Range: -4.2097
Max Act: 3.7563. Min Act: -0.1700
Data Index: 108572 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2097. Min Range: -4.2097
Max Act: 3.7563. Min Act: -0.1700
Data Index: 5626017 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2097. Min Range: -4.2097
Max Act: 3.7563. Min Act: -0.1700
Data Index: 2218274 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #19