Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4318 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9624. Min Range: -6.9624
Max Act: 6.9624. Min Act: -0.1700
Data Index: 6459469 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9624. Min Range: -6.9624
Max Act: 6.8687. Min Act: -0.1700
Data Index: 8538317 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9624. Min Range: -6.9624
Max Act: 6.8374. Min Act: -0.1700
Data Index: 7919818 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9624. Min Range: -6.9624
Max Act: 6.7749. Min Act: -0.1700
Data Index: 1959044 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9624. Min Range: -6.9624
Max Act: 6.7749. Min Act: -0.1700
Data Index: 8538328 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9624. Min Range: -6.9624
Max Act: 6.7437. Min Act: -0.1700
Data Index: 1404119 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9624. Min Range: -6.9624
Max Act: 6.6499. Min Act: -0.1700
Data Index: 7140332 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9624. Min Range: -6.9624
Max Act: 6.6187. Min Act: -0.1700
Data Index: 128669 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9624. Min Range: -6.9624
Max Act: 6.5874. Min Act: -0.1700
Data Index: 348356 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9624. Min Range: -6.9624
Max Act: 6.5874. Min Act: -0.1700
Data Index: 348339 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9624. Min Range: -6.9624
Max Act: 6.5874. Min Act: -0.1700
Data Index: 2137435 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9624. Min Range: -6.9624
Max Act: 6.5562. Min Act: -0.1700
Data Index: 4656586 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9624. Min Range: -6.9624
Max Act: 6.5562. Min Act: -0.1700
Data Index: 7346706 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9624. Min Range: -6.9624
Max Act: 6.5249. Min Act: -0.1700
Data Index: 3288727 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9624. Min Range: -6.9624
Max Act: 6.5562. Min Act: -0.1700
Data Index: 7078412 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9624. Min Range: -6.9624
Max Act: 6.5249. Min Act: -0.1700
Data Index: 4656597 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9624. Min Range: -6.9624
Max Act: 6.5562. Min Act: -0.1700
Data Index: 3480279 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9624. Min Range: -6.9624
Max Act: 6.5562. Min Act: -0.1700
Data Index: 7644224 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9624. Min Range: -6.9624
Max Act: 6.5562. Min Act: -0.1700
Data Index: 2137424 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9624. Min Range: -6.9624
Max Act: 6.5249. Min Act: -0.1700
Data Index: 7644234 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #19