Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1039 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2894. Min Range: -5.2894
Max Act: 5.2894. Min Act: -0.1700
Data Index: 2513553 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2894. Min Range: -5.2894
Max Act: 5.2894. Min Act: -0.1700
Data Index: 5489642 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2894. Min Range: -5.2894
Max Act: 5.2269. Min Act: -0.1700
Data Index: 1211480 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2894. Min Range: -5.2894
Max Act: 5.1644. Min Act: -0.1700
Data Index: 7501320 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2894. Min Range: -5.2894
Max Act: 5.1957. Min Act: -0.1700
Data Index: 4575042 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2894. Min Range: -5.2894
Max Act: 5.1644. Min Act: -0.1700
Data Index: 5470383 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2894. Min Range: -5.2894
Max Act: 5.1644. Min Act: -0.1700
Data Index: 7480109 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2894. Min Range: -5.2894
Max Act: 5.1332. Min Act: -0.1700
Data Index: 7984353 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2894. Min Range: -5.2894
Max Act: 5.1019. Min Act: -0.1700
Data Index: 2190267 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2894. Min Range: -5.2894
Max Act: 5.0707. Min Act: -0.1700
Data Index: 951619 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2894. Min Range: -5.2894
Max Act: 5.0707. Min Act: -0.1700
Data Index: 3197254 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2894. Min Range: -5.2894
Max Act: 5.0394. Min Act: -0.1700
Data Index: 2767005 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2894. Min Range: -5.2894
Max Act: 5.0394. Min Act: -0.1700
Data Index: 1508944 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2894. Min Range: -5.2894
Max Act: 5.0394. Min Act: -0.1700
Data Index: 2221028 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2894. Min Range: -5.2894
Max Act: 5.0082. Min Act: -0.1700
Data Index: 2067409 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2894. Min Range: -5.2894
Max Act: 5.0394. Min Act: -0.1700
Data Index: 6589599 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2894. Min Range: -5.2894
Max Act: 5.0082. Min Act: -0.1700
Data Index: 2026901 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2894. Min Range: -5.2894
Max Act: 5.0082. Min Act: -0.1700
Data Index: 2644587 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2894. Min Range: -5.2894
Max Act: 5.0082. Min Act: -0.1700
Data Index: 3061818 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2894. Min Range: -5.2894
Max Act: 4.9769. Min Act: -0.1700
Data Index: 4702029 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #19