Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5264 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7928. Min Range: -5.7928
Max Act: 5.7928. Min Act: -0.1700
Data Index: 1321568 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7928. Min Range: -5.7928
Max Act: 5.2928. Min Act: -0.1700
Data Index: 4084790 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7928. Min Range: -5.7928
Max Act: 5.1678. Min Act: -0.1700
Data Index: 2135035 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7928. Min Range: -5.7928
Max Act: 5.1053. Min Act: -0.1700
Data Index: 3003793 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7928. Min Range: -5.7928
Max Act: 5.0740. Min Act: -0.1700
Data Index: 2019372 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7928. Min Range: -5.7928
Max Act: 5.0428. Min Act: -0.1700
Data Index: 7053276 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7928. Min Range: -5.7928
Max Act: 5.0428. Min Act: -0.1700
Data Index: 3907226 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7928. Min Range: -5.7928
Max Act: 5.0115. Min Act: -0.1700
Data Index: 7631921 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7928. Min Range: -5.7928
Max Act: 4.9803. Min Act: -0.1700
Data Index: 5241628 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7928. Min Range: -5.7928
Max Act: 4.9490. Min Act: -0.1700
Data Index: 841924 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7928. Min Range: -5.7928
Max Act: 4.9178. Min Act: -0.1700
Data Index: 1461884 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7928. Min Range: -5.7928
Max Act: 4.8553. Min Act: -0.1700
Data Index: 5191861 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7928. Min Range: -5.7928
Max Act: 4.8865. Min Act: -0.1700
Data Index: 2768465 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7928. Min Range: -5.7928
Max Act: 4.8553. Min Act: -0.1700
Data Index: 4324249 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7928. Min Range: -5.7928
Max Act: 4.8553. Min Act: -0.1700
Data Index: 7034938 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7928. Min Range: -5.7928
Max Act: 4.7928. Min Act: -0.1700
Data Index: 3424264 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7928. Min Range: -5.7928
Max Act: 4.8553. Min Act: -0.1700
Data Index: 3982385 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7928. Min Range: -5.7928
Max Act: 4.7928. Min Act: -0.1700
Data Index: 3787554 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7928. Min Range: -5.7928
Max Act: 4.7615. Min Act: -0.1700
Data Index: 3220737 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7928. Min Range: -5.7928
Max Act: 4.7928. Min Act: -0.1700
Data Index: 7926402 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #19