Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2892 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8082. Min Range: -7.8082
Max Act: 7.8082. Min Act: -0.1700
Data Index: 3581569 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8082. Min Range: -7.8082
Max Act: 7.4644. Min Act: -0.1700
Data Index: 2226283 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8082. Min Range: -7.8082
Max Act: 7.2769. Min Act: -0.1700
Data Index: 2755540 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8082. Min Range: -7.8082
Max Act: 7.1832. Min Act: -0.1700
Data Index: 7557754 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8082. Min Range: -7.8082
Max Act: 7.0894. Min Act: -0.1700
Data Index: 5402996 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8082. Min Range: -7.8082
Max Act: 7.0269. Min Act: -0.1700
Data Index: 7026676 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8082. Min Range: -7.8082
Max Act: 7.0269. Min Act: -0.1700
Data Index: 319787 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8082. Min Range: -7.8082
Max Act: 6.9957. Min Act: -0.1700
Data Index: 6240810 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8082. Min Range: -7.8082
Max Act: 6.9957. Min Act: -0.1700
Data Index: 7264587 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8082. Min Range: -7.8082
Max Act: 6.9644. Min Act: -0.1700
Data Index: 1434109 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8082. Min Range: -7.8082
Max Act: 6.8707. Min Act: -0.1700
Data Index: 6532712 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8082. Min Range: -7.8082
Max Act: 6.8707. Min Act: -0.1700
Data Index: 1225521 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8082. Min Range: -7.8082
Max Act: 6.9019. Min Act: -0.1700
Data Index: 6858072 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8082. Min Range: -7.8082
Max Act: 6.8707. Min Act: -0.1700
Data Index: 3142508 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8082. Min Range: -7.8082
Max Act: 6.8394. Min Act: -0.1700
Data Index: 8632735 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8082. Min Range: -7.8082
Max Act: 6.8394. Min Act: -0.1700
Data Index: 5296091 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8082. Min Range: -7.8082
Max Act: 6.8082. Min Act: -0.1700
Data Index: 6611065 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8082. Min Range: -7.8082
Max Act: 6.8082. Min Act: -0.1700
Data Index: 7775903 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8082. Min Range: -7.8082
Max Act: 6.8082. Min Act: -0.1700
Data Index: 1937735 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8082. Min Range: -7.8082
Max Act: 6.8082. Min Act: -0.1700
Data Index: 6858070 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #19