Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 354 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7838. Min Range: -6.7838
Max Act: 6.7838. Min Act: -0.1700
Data Index: 5214533 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7838. Min Range: -6.7838
Max Act: 6.7526. Min Act: -0.1700
Data Index: 3121454 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7838. Min Range: -6.7838
Max Act: 6.5963. Min Act: -0.1700
Data Index: 8146304 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7838. Min Range: -6.7838
Max Act: 6.5026. Min Act: -0.1700
Data Index: 2623707 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7838. Min Range: -6.7838
Max Act: 6.5026. Min Act: -0.1700
Data Index: 2544549 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7838. Min Range: -6.7838
Max Act: 6.4401. Min Act: -0.1700
Data Index: 2671015 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7838. Min Range: -6.7838
Max Act: 6.4088. Min Act: -0.1700
Data Index: 2817971 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7838. Min Range: -6.7838
Max Act: 6.3776. Min Act: -0.1700
Data Index: 2415930 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7838. Min Range: -6.7838
Max Act: 6.3776. Min Act: -0.1700
Data Index: 6562694 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7838. Min Range: -6.7838
Max Act: 6.3463. Min Act: -0.1700
Data Index: 7413372 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7838. Min Range: -6.7838
Max Act: 6.3151. Min Act: -0.1700
Data Index: 8746023 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7838. Min Range: -6.7838
Max Act: 6.2838. Min Act: -0.1700
Data Index: 4522657 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7838. Min Range: -6.7838
Max Act: 6.2213. Min Act: -0.1700
Data Index: 8705434 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7838. Min Range: -6.7838
Max Act: 6.2213. Min Act: -0.1700
Data Index: 4621648 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7838. Min Range: -6.7838
Max Act: 6.1901. Min Act: -0.1700
Data Index: 5661536 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7838. Min Range: -6.7838
Max Act: 6.1901. Min Act: -0.1700
Data Index: 822117 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7838. Min Range: -6.7838
Max Act: 6.1588. Min Act: -0.1700
Data Index: 730055 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7838. Min Range: -6.7838
Max Act: 6.1276. Min Act: -0.1700
Data Index: 456298 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7838. Min Range: -6.7838
Max Act: 6.1588. Min Act: -0.1700
Data Index: 1034601 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7838. Min Range: -6.7838
Max Act: 6.1276. Min Act: -0.1700
Data Index: 4276197 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #19