Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1899 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4213. Min Range: -5.4213
Max Act: 5.4213. Min Act: -0.1700
Data Index: 994911 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4213. Min Range: -5.4213
Max Act: 5.3275. Min Act: -0.1700
Data Index: 171164 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4213. Min Range: -5.4213
Max Act: 5.2338. Min Act: -0.1700
Data Index: 8550593 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4213. Min Range: -5.4213
Max Act: 5.2338. Min Act: -0.1700
Data Index: 3962919 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4213. Min Range: -5.4213
Max Act: 5.1713. Min Act: -0.1700
Data Index: 5351715 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4213. Min Range: -5.4213
Max Act: 5.1713. Min Act: -0.1700
Data Index: 6376983 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4213. Min Range: -5.4213
Max Act: 5.1088. Min Act: -0.1700
Data Index: 5750221 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4213. Min Range: -5.4213
Max Act: 5.0775. Min Act: -0.1700
Data Index: 6054359 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4213. Min Range: -5.4213
Max Act: 5.0150. Min Act: -0.1700
Data Index: 1767427 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4213. Min Range: -5.4213
Max Act: 5.0150. Min Act: -0.1700
Data Index: 8757092 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4213. Min Range: -5.4213
Max Act: 4.9838. Min Act: -0.1700
Data Index: 8160021 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4213. Min Range: -5.4213
Max Act: 4.9838. Min Act: -0.1700
Data Index: 6838779 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4213. Min Range: -5.4213
Max Act: 4.9838. Min Act: -0.1700
Data Index: 2364526 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4213. Min Range: -5.4213
Max Act: 4.9838. Min Act: -0.1700
Data Index: 5735512 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4213. Min Range: -5.4213
Max Act: 4.9525. Min Act: -0.1700
Data Index: 6361166 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4213. Min Range: -5.4213
Max Act: 4.9525. Min Act: -0.1700
Data Index: 7983543 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4213. Min Range: -5.4213
Max Act: 4.9525. Min Act: -0.1700
Data Index: 4258840 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4213. Min Range: -5.4213
Max Act: 4.9525. Min Act: -0.1700
Data Index: 1811655 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4213. Min Range: -5.4213
Max Act: 4.9525. Min Act: -0.1700
Data Index: 1097003 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4213. Min Range: -5.4213
Max Act: 4.9525. Min Act: -0.1700
Data Index: 5211750 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #19