Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6186 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3437. Min Range: -8.3437
Max Act: 8.3437. Min Act: -0.1700
Data Index: 6070414 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3437. Min Range: -8.3437
Max Act: 7.6562. Min Act: -0.1700
Data Index: 6514485 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3437. Min Range: -8.3437
Max Act: 7.4374. Min Act: -0.1700
Data Index: 4350948 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3437. Min Range: -8.3437
Max Act: 7.4374. Min Act: -0.1700
Data Index: 8304190 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3437. Min Range: -8.3437
Max Act: 7.4374. Min Act: -0.1700
Data Index: 862593 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3437. Min Range: -8.3437
Max Act: 7.3749. Min Act: -0.1700
Data Index: 6123203 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3437. Min Range: -8.3437
Max Act: 7.3749. Min Act: -0.1700
Data Index: 4636233 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3437. Min Range: -8.3437
Max Act: 7.3437. Min Act: -0.1700
Data Index: 2292050 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3437. Min Range: -8.3437
Max Act: 7.2499. Min Act: -0.1700
Data Index: 1485978 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3437. Min Range: -8.3437
Max Act: 7.2812. Min Act: -0.1700
Data Index: 4646850 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3437. Min Range: -8.3437
Max Act: 7.2187. Min Act: -0.1700
Data Index: 989864 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3437. Min Range: -8.3437
Max Act: 7.1874. Min Act: -0.1700
Data Index: 996944 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3437. Min Range: -8.3437
Max Act: 7.1249. Min Act: -0.1700
Data Index: 7520065 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3437. Min Range: -8.3437
Max Act: 7.1562. Min Act: -0.1700
Data Index: 8634205 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3437. Min Range: -8.3437
Max Act: 7.1249. Min Act: -0.1700
Data Index: 1857889 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3437. Min Range: -8.3437
Max Act: 7.1249. Min Act: -0.1700
Data Index: 8278562 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3437. Min Range: -8.3437
Max Act: 7.0937. Min Act: -0.1700
Data Index: 5859670 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3437. Min Range: -8.3437
Max Act: 7.0937. Min Act: -0.1700
Data Index: 487517 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3437. Min Range: -8.3437
Max Act: 7.0624. Min Act: -0.1700
Data Index: 4612296 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3437. Min Range: -8.3437
Max Act: 7.0624. Min Act: -0.1700
Data Index: 6253541 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #19