Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3224 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2470. Min Range: -8.2470
Max Act: 8.2470. Min Act: -0.1700
Data Index: 1645619 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2470. Min Range: -8.2470
Max Act: 8.0595. Min Act: -0.1700
Data Index: 2981362 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2470. Min Range: -8.2470
Max Act: 8.0595. Min Act: -0.1700
Data Index: 4633240 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2470. Min Range: -8.2470
Max Act: 7.9970. Min Act: -0.1700
Data Index: 2601852 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2470. Min Range: -8.2470
Max Act: 8.0595. Min Act: -0.1700
Data Index: 1051654 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2470. Min Range: -8.2470
Max Act: 7.9345. Min Act: -0.1700
Data Index: 5735405 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2470. Min Range: -8.2470
Max Act: 7.8720. Min Act: -0.1700
Data Index: 5622378 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2470. Min Range: -8.2470
Max Act: 7.8407. Min Act: -0.1700
Data Index: 8426296 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2470. Min Range: -8.2470
Max Act: 7.8095. Min Act: -0.1700
Data Index: 413742 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2470. Min Range: -8.2470
Max Act: 7.7782. Min Act: -0.1700
Data Index: 1641799 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2470. Min Range: -8.2470
Max Act: 7.7782. Min Act: -0.1700
Data Index: 445050 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2470. Min Range: -8.2470
Max Act: 7.6845. Min Act: -0.1700
Data Index: 637264 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2470. Min Range: -8.2470
Max Act: 7.6532. Min Act: -0.1700
Data Index: 1830783 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2470. Min Range: -8.2470
Max Act: 7.5907. Min Act: -0.1700
Data Index: 3485135 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2470. Min Range: -8.2470
Max Act: 7.5907. Min Act: -0.1700
Data Index: 4014431 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2470. Min Range: -8.2470
Max Act: 7.6220. Min Act: -0.1700
Data Index: 1079690 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2470. Min Range: -8.2470
Max Act: 7.6220. Min Act: -0.1700
Data Index: 2013219 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2470. Min Range: -8.2470
Max Act: 7.5907. Min Act: -0.1700
Data Index: 5911067 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2470. Min Range: -8.2470
Max Act: 7.5907. Min Act: -0.1700
Data Index: 2030519 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2470. Min Range: -8.2470
Max Act: 7.5595. Min Act: -0.1700
Data Index: 5633913 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #19