Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3224 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9802. Min Range: -4.9802
Max Act: 4.9802. Min Act: -0.1700
Data Index: 1124487 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9802. Min Range: -4.9802
Max Act: 4.9490. Min Act: -0.1700
Data Index: 230376 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9802. Min Range: -4.9802
Max Act: 4.8240. Min Act: -0.1700
Data Index: 1124486 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9802. Min Range: -4.9802
Max Act: 4.6365. Min Act: -0.1700
Data Index: 1610829 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9802. Min Range: -4.9802
Max Act: 4.6365. Min Act: -0.1700
Data Index: 8199430 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9802. Min Range: -4.9802
Max Act: 4.6365. Min Act: -0.1700
Data Index: 8748737 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9802. Min Range: -4.9802
Max Act: 4.6052. Min Act: -0.1700
Data Index: 6923196 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9802. Min Range: -4.9802
Max Act: 4.6052. Min Act: -0.1700
Data Index: 5706175 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9802. Min Range: -4.9802
Max Act: 4.6052. Min Act: -0.1700
Data Index: 8238808 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9802. Min Range: -4.9802
Max Act: 4.5740. Min Act: -0.1700
Data Index: 2846619 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9802. Min Range: -4.9802
Max Act: 4.5740. Min Act: -0.1700
Data Index: 71025 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9802. Min Range: -4.9802
Max Act: 4.5427. Min Act: -0.1700
Data Index: 2182551 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9802. Min Range: -4.9802
Max Act: 4.5427. Min Act: -0.1700
Data Index: 1832898 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9802. Min Range: -4.9802
Max Act: 4.5427. Min Act: -0.1700
Data Index: 44787 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9802. Min Range: -4.9802
Max Act: 4.5427. Min Act: -0.1700
Data Index: 5734530 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9802. Min Range: -4.9802
Max Act: 4.5427. Min Act: -0.1700
Data Index: 2486514 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9802. Min Range: -4.9802
Max Act: 4.5427. Min Act: -0.1700
Data Index: 4800640 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9802. Min Range: -4.9802
Max Act: 4.5115. Min Act: -0.1700
Data Index: 5577934 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9802. Min Range: -4.9802
Max Act: 4.5115. Min Act: -0.1700
Data Index: 3308126 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9802. Min Range: -4.9802
Max Act: 4.5115. Min Act: -0.1700
Data Index: 4109879 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #19