Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3258 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7052. Min Range: -7.7052
Max Act: 7.7052. Min Act: -0.1700
Data Index: 1142114 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7052. Min Range: -7.7052
Max Act: 7.6427. Min Act: -0.1700
Data Index: 3263619 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7052. Min Range: -7.7052
Max Act: 7.5490. Min Act: -0.1700
Data Index: 6234494 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7052. Min Range: -7.7052
Max Act: 7.5490. Min Act: -0.1700
Data Index: 7247591 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7052. Min Range: -7.7052
Max Act: 7.3927. Min Act: -0.1700
Data Index: 3632634 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7052. Min Range: -7.7052
Max Act: 7.3302. Min Act: -0.1700
Data Index: 4156516 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7052. Min Range: -7.7052
Max Act: 7.3302. Min Act: -0.1700
Data Index: 2834215 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7052. Min Range: -7.7052
Max Act: 7.2990. Min Act: -0.1700
Data Index: 3652851 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7052. Min Range: -7.7052
Max Act: 7.2365. Min Act: -0.1700
Data Index: 3408054 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7052. Min Range: -7.7052
Max Act: 7.2052. Min Act: -0.1700
Data Index: 8585867 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7052. Min Range: -7.7052
Max Act: 7.2052. Min Act: -0.1700
Data Index: 8313504 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7052. Min Range: -7.7052
Max Act: 7.1427. Min Act: -0.1700
Data Index: 178682 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7052. Min Range: -7.7052
Max Act: 7.1115. Min Act: -0.1700
Data Index: 7078471 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7052. Min Range: -7.7052
Max Act: 7.1115. Min Act: -0.1700
Data Index: 6307175 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7052. Min Range: -7.7052
Max Act: 7.1115. Min Act: -0.1700
Data Index: 7618894 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7052. Min Range: -7.7052
Max Act: 7.1115. Min Act: -0.1700
Data Index: 8687788 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7052. Min Range: -7.7052
Max Act: 7.1427. Min Act: -0.1700
Data Index: 8762293 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7052. Min Range: -7.7052
Max Act: 7.1115. Min Act: -0.1700
Data Index: 5493584 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7052. Min Range: -7.7052
Max Act: 7.0802. Min Act: -0.1700
Data Index: 5092669 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7052. Min Range: -7.7052
Max Act: 7.0802. Min Act: -0.1700
Data Index: 981944 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #19