Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4453 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 16.9178. Min Range: -16.9178
Max Act: 16.9178. Min Act: -0.1700
Data Index: 833881 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 16.9178. Min Range: -16.9178
Max Act: 16.7928. Min Act: -0.1700
Data Index: 8554306 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 16.9178. Min Range: -16.9178
Max Act: 16.4178. Min Act: -0.1700
Data Index: 500178 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 16.9178. Min Range: -16.9178
Max Act: 16.4178. Min Act: -0.1700
Data Index: 3861136 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 16.9178. Min Range: -16.9178
Max Act: 16.2928. Min Act: -0.1700
Data Index: 3010965 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 16.9178. Min Range: -16.9178
Max Act: 16.2928. Min Act: -0.1700
Data Index: 1696156 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 16.9178. Min Range: -16.9178
Max Act: 16.2928. Min Act: -0.1700
Data Index: 8075401 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 16.9178. Min Range: -16.9178
Max Act: 16.2928. Min Act: -0.1700
Data Index: 4202203 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 16.9178. Min Range: -16.9178
Max Act: 16.2928. Min Act: -0.1700
Data Index: 6992534 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 16.9178. Min Range: -16.9178
Max Act: 16.2928. Min Act: -0.1700
Data Index: 4195731 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 16.9178. Min Range: -16.9178
Max Act: 16.2928. Min Act: -0.1700
Data Index: 6355530 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 16.9178. Min Range: -16.9178
Max Act: 16.2928. Min Act: -0.1700
Data Index: 6344390 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 16.9178. Min Range: -16.9178
Max Act: 16.2928. Min Act: -0.1700
Data Index: 5957831 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 16.9178. Min Range: -16.9178
Max Act: 16.2928. Min Act: -0.1700
Data Index: 5804028 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 16.9178. Min Range: -16.9178
Max Act: 16.2928. Min Act: -0.1700
Data Index: 5763339 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 16.9178. Min Range: -16.9178
Max Act: 16.2928. Min Act: -0.1700
Data Index: 5486550 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 16.9178. Min Range: -16.9178
Max Act: 16.2928. Min Act: -0.1700
Data Index: 4589110 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 16.9178. Min Range: -16.9178
Max Act: 16.2928. Min Act: -0.1700
Data Index: 344470 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 16.9178. Min Range: -16.9178
Max Act: 16.2928. Min Act: -0.1700
Data Index: 4587422 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 16.9178. Min Range: -16.9178
Max Act: 16.1678. Min Act: -0.1700
Data Index: 4203317 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #19