Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5442 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5519. Min Range: -7.5519
Max Act: 7.5519. Min Act: -0.1700
Data Index: 5863862 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5519. Min Range: -7.5519
Max Act: 7.4582. Min Act: -0.1700
Data Index: 5749414 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5519. Min Range: -7.5519
Max Act: 7.1769. Min Act: -0.1700
Data Index: 1376028 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5519. Min Range: -7.5519
Max Act: 7.0519. Min Act: -0.1700
Data Index: 838139 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5519. Min Range: -7.5519
Max Act: 6.9894. Min Act: -0.1700
Data Index: 2787802 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5519. Min Range: -7.5519
Max Act: 6.9269. Min Act: -0.1700
Data Index: 7279088 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5519. Min Range: -7.5519
Max Act: 6.8957. Min Act: -0.1700
Data Index: 436610 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5519. Min Range: -7.5519
Max Act: 6.8957. Min Act: -0.1700
Data Index: 7346610 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5519. Min Range: -7.5519
Max Act: 6.8644. Min Act: -0.1700
Data Index: 4445022 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5519. Min Range: -7.5519
Max Act: 6.8019. Min Act: -0.1700
Data Index: 11833 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5519. Min Range: -7.5519
Max Act: 6.7707. Min Act: -0.1700
Data Index: 6267816 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5519. Min Range: -7.5519
Max Act: 6.7394. Min Act: -0.1700
Data Index: 7636352 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5519. Min Range: -7.5519
Max Act: 6.7394. Min Act: -0.1700
Data Index: 7756607 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5519. Min Range: -7.5519
Max Act: 6.7394. Min Act: -0.1700
Data Index: 6832328 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5519. Min Range: -7.5519
Max Act: 6.7394. Min Act: -0.1700
Data Index: 3884442 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5519. Min Range: -7.5519
Max Act: 6.7082. Min Act: -0.1700
Data Index: 6231779 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5519. Min Range: -7.5519
Max Act: 6.7082. Min Act: -0.1700
Data Index: 3909980 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5519. Min Range: -7.5519
Max Act: 6.7082. Min Act: -0.1700
Data Index: 3317999 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5519. Min Range: -7.5519
Max Act: 6.7082. Min Act: -0.1700
Data Index: 4135300 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5519. Min Range: -7.5519
Max Act: 6.6769. Min Act: -0.1700
Data Index: 3495871 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #19