Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 13 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3284. Min Range: -6.3284
Max Act: 6.3284. Min Act: -0.1700
Data Index: 5318971 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3284. Min Range: -6.3284
Max Act: 6.2659. Min Act: -0.1700
Data Index: 2018684 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3284. Min Range: -6.3284
Max Act: 6.2971. Min Act: -0.1700
Data Index: 899427 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3284. Min Range: -6.3284
Max Act: 6.2346. Min Act: -0.1700
Data Index: 8321504 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3284. Min Range: -6.3284
Max Act: 6.2346. Min Act: -0.1700
Data Index: 7210742 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3284. Min Range: -6.3284
Max Act: 6.2034. Min Act: -0.1700
Data Index: 8295835 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3284. Min Range: -6.3284
Max Act: 6.1721. Min Act: -0.1700
Data Index: 1031314 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3284. Min Range: -6.3284
Max Act: 6.1721. Min Act: -0.1700
Data Index: 1515996 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3284. Min Range: -6.3284
Max Act: 6.1096. Min Act: -0.1700
Data Index: 1541173 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3284. Min Range: -6.3284
Max Act: 6.1096. Min Act: -0.1700
Data Index: 7726572 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3284. Min Range: -6.3284
Max Act: 6.1096. Min Act: -0.1700
Data Index: 436896 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3284. Min Range: -6.3284
Max Act: 6.0784. Min Act: -0.1700
Data Index: 5761008 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3284. Min Range: -6.3284
Max Act: 6.0471. Min Act: -0.1700
Data Index: 4305286 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3284. Min Range: -6.3284
Max Act: 6.0471. Min Act: -0.1700
Data Index: 8021161 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3284. Min Range: -6.3284
Max Act: 6.0471. Min Act: -0.1700
Data Index: 5024777 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3284. Min Range: -6.3284
Max Act: 6.0159. Min Act: -0.1700
Data Index: 1365303 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3284. Min Range: -6.3284
Max Act: 6.0159. Min Act: -0.1700
Data Index: 311012 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3284. Min Range: -6.3284
Max Act: 6.0159. Min Act: -0.1700
Data Index: 8029808 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3284. Min Range: -6.3284
Max Act: 6.0159. Min Act: -0.1700
Data Index: 926115 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3284. Min Range: -6.3284
Max Act: 6.0159. Min Act: -0.1700
Data Index: 7954710 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #19