Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 324 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2594. Min Range: -7.2594
Max Act: 7.2594. Min Act: -0.1700
Data Index: 1150787 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2594. Min Range: -7.2594
Max Act: 7.1344. Min Act: -0.1700
Data Index: 6040913 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2594. Min Range: -7.2594
Max Act: 7.0719. Min Act: -0.1700
Data Index: 3845316 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2594. Min Range: -7.2594
Max Act: 7.0719. Min Act: -0.1700
Data Index: 5888292 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2594. Min Range: -7.2594
Max Act: 7.0719. Min Act: -0.1700
Data Index: 714866 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2594. Min Range: -7.2594
Max Act: 7.0719. Min Act: -0.1700
Data Index: 5262853 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2594. Min Range: -7.2594
Max Act: 7.0719. Min Act: -0.1700
Data Index: 8031414 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2594. Min Range: -7.2594
Max Act: 7.0094. Min Act: -0.1700
Data Index: 4577275 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2594. Min Range: -7.2594
Max Act: 7.0094. Min Act: -0.1700
Data Index: 577673 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2594. Min Range: -7.2594
Max Act: 7.0094. Min Act: -0.1700
Data Index: 8307253 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2594. Min Range: -7.2594
Max Act: 7.0094. Min Act: -0.1700
Data Index: 4981791 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2594. Min Range: -7.2594
Max Act: 7.0094. Min Act: -0.1700
Data Index: 5389666 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2594. Min Range: -7.2594
Max Act: 7.0094. Min Act: -0.1700
Data Index: 974869 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2594. Min Range: -7.2594
Max Act: 7.0094. Min Act: -0.1700
Data Index: 1344044 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2594. Min Range: -7.2594
Max Act: 7.0094. Min Act: -0.1700
Data Index: 672291 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2594. Min Range: -7.2594
Max Act: 7.0094. Min Act: -0.1700
Data Index: 2418824 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2594. Min Range: -7.2594
Max Act: 7.0094. Min Act: -0.1700
Data Index: 6900995 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2594. Min Range: -7.2594
Max Act: 7.0094. Min Act: -0.1700
Data Index: 2681109 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2594. Min Range: -7.2594
Max Act: 7.0094. Min Act: -0.1700
Data Index: 551237 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2594. Min Range: -7.2594
Max Act: 7.0094. Min Act: -0.1700
Data Index: 3597621 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #19