Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 33 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8025. Min Range: -8.8025
Max Act: 8.8025. Min Act: -0.1700
Data Index: 4393691 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8025. Min Range: -8.8025
Max Act: 8.6150. Min Act: -0.1700
Data Index: 3771567 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8025. Min Range: -8.8025
Max Act: 8.4900. Min Act: -0.1700
Data Index: 5808671 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8025. Min Range: -8.8025
Max Act: 8.4275. Min Act: -0.1700
Data Index: 7855386 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8025. Min Range: -8.8025
Max Act: 8.4275. Min Act: -0.1700
Data Index: 7702036 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8025. Min Range: -8.8025
Max Act: 8.3025. Min Act: -0.1700
Data Index: 6726008 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8025. Min Range: -8.8025
Max Act: 8.3025. Min Act: -0.1700
Data Index: 5526133 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8025. Min Range: -8.8025
Max Act: 8.2400. Min Act: -0.1700
Data Index: 8106940 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8025. Min Range: -8.8025
Max Act: 8.2400. Min Act: -0.1700
Data Index: 2141971 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8025. Min Range: -8.8025
Max Act: 8.2400. Min Act: -0.1700
Data Index: 8726111 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8025. Min Range: -8.8025
Max Act: 8.1775. Min Act: -0.1700
Data Index: 1771596 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8025. Min Range: -8.8025
Max Act: 8.1775. Min Act: -0.1700
Data Index: 226834 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8025. Min Range: -8.8025
Max Act: 8.1150. Min Act: -0.1700
Data Index: 3554193 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8025. Min Range: -8.8025
Max Act: 8.1775. Min Act: -0.1700
Data Index: 5146719 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8025. Min Range: -8.8025
Max Act: 8.1150. Min Act: -0.1700
Data Index: 8827842 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8025. Min Range: -8.8025
Max Act: 8.1150. Min Act: -0.1700
Data Index: 8636047 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8025. Min Range: -8.8025
Max Act: 8.0525. Min Act: -0.1700
Data Index: 4316261 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8025. Min Range: -8.8025
Max Act: 8.0525. Min Act: -0.1700
Data Index: 7453675 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8025. Min Range: -8.8025
Max Act: 8.0525. Min Act: -0.1700
Data Index: 4831866 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8025. Min Range: -8.8025
Max Act: 8.0525. Min Act: -0.1700
Data Index: 3256502 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #19