Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4453 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2950. Min Range: -8.2950
Max Act: 8.2950. Min Act: -0.1700
Data Index: 2910056 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2950. Min Range: -8.2950
Max Act: 8.2325. Min Act: -0.1700
Data Index: 1243865 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2950. Min Range: -8.2950
Max Act: 8.0137. Min Act: -0.1700
Data Index: 7339143 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2950. Min Range: -8.2950
Max Act: 7.9200. Min Act: -0.1700
Data Index: 4528834 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2950. Min Range: -8.2950
Max Act: 7.8887. Min Act: -0.1700
Data Index: 6197387 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2950. Min Range: -8.2950
Max Act: 7.8262. Min Act: -0.1700
Data Index: 3216946 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2950. Min Range: -8.2950
Max Act: 7.7950. Min Act: -0.1700
Data Index: 1769958 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2950. Min Range: -8.2950
Max Act: 7.7637. Min Act: -0.1700
Data Index: 7564985 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2950. Min Range: -8.2950
Max Act: 7.7637. Min Act: -0.1700
Data Index: 7252129 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2950. Min Range: -8.2950
Max Act: 7.6387. Min Act: -0.1700
Data Index: 8516933 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2950. Min Range: -8.2950
Max Act: 7.6700. Min Act: -0.1700
Data Index: 906967 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2950. Min Range: -8.2950
Max Act: 7.6075. Min Act: -0.1700
Data Index: 2544893 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2950. Min Range: -8.2950
Max Act: 7.6075. Min Act: -0.1700
Data Index: 5108396 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2950. Min Range: -8.2950
Max Act: 7.5762. Min Act: -0.1700
Data Index: 8198819 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2950. Min Range: -8.2950
Max Act: 7.5450. Min Act: -0.1700
Data Index: 5012715 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2950. Min Range: -8.2950
Max Act: 7.5450. Min Act: -0.1700
Data Index: 2513066 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2950. Min Range: -8.2950
Max Act: 7.5137. Min Act: -0.1700
Data Index: 2155970 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2950. Min Range: -8.2950
Max Act: 7.4512. Min Act: -0.1700
Data Index: 1217688 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2950. Min Range: -8.2950
Max Act: 7.4512. Min Act: -0.1700
Data Index: 2740704 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2950. Min Range: -8.2950
Max Act: 7.4200. Min Act: -0.1700
Data Index: 3463354 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #19