Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2756 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3665. Min Range: -8.3665
Max Act: 8.3665. Min Act: -0.1700
Data Index: 8176728 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3665. Min Range: -8.3665
Max Act: 7.9915. Min Act: -0.1700
Data Index: 8366599 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3665. Min Range: -8.3665
Max Act: 8.0228. Min Act: -0.1700
Data Index: 537455 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3665. Min Range: -8.3665
Max Act: 8.0228. Min Act: -0.1700
Data Index: 7284801 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3665. Min Range: -8.3665
Max Act: 7.8665. Min Act: -0.1700
Data Index: 6732883 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3665. Min Range: -8.3665
Max Act: 7.8978. Min Act: -0.1700
Data Index: 6320965 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3665. Min Range: -8.3665
Max Act: 7.8665. Min Act: -0.1700
Data Index: 1086886 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3665. Min Range: -8.3665
Max Act: 7.8353. Min Act: -0.1700
Data Index: 6752212 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3665. Min Range: -8.3665
Max Act: 7.8353. Min Act: -0.1700
Data Index: 4545540 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3665. Min Range: -8.3665
Max Act: 7.8040. Min Act: -0.1700
Data Index: 1047421 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3665. Min Range: -8.3665
Max Act: 7.7728. Min Act: -0.1700
Data Index: 5139479 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3665. Min Range: -8.3665
Max Act: 7.7103. Min Act: -0.1700
Data Index: 8508151 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3665. Min Range: -8.3665
Max Act: 7.6790. Min Act: -0.1700
Data Index: 1590436 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3665. Min Range: -8.3665
Max Act: 7.6790. Min Act: -0.1700
Data Index: 7253926 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3665. Min Range: -8.3665
Max Act: 7.6790. Min Act: -0.1700
Data Index: 7963583 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3665. Min Range: -8.3665
Max Act: 7.6478. Min Act: -0.1700
Data Index: 753248 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3665. Min Range: -8.3665
Max Act: 7.6165. Min Act: -0.1700
Data Index: 5299528 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3665. Min Range: -8.3665
Max Act: 7.5853. Min Act: -0.1700
Data Index: 3868190 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3665. Min Range: -8.3665
Max Act: 7.5853. Min Act: -0.1700
Data Index: 341670 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3665. Min Range: -8.3665
Max Act: 7.5853. Min Act: -0.1700
Data Index: 4468293 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #19