Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2167 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.1572. Min Range: -3.1572
Max Act: 3.1572. Min Act: -0.1700
Data Index: 3111889 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1572. Min Range: -3.1572
Max Act: 3.1415. Min Act: -0.1700
Data Index: 3579866 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1572. Min Range: -3.1572
Max Act: 3.1258. Min Act: -0.1700
Data Index: 3710499 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1572. Min Range: -3.1572
Max Act: 3.1100. Min Act: -0.1700
Data Index: 7828685 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1572. Min Range: -3.1572
Max Act: 3.0311. Min Act: -0.1700
Data Index: 6380704 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1572. Min Range: -3.1572
Max Act: 3.0311. Min Act: -0.1700
Data Index: 5271992 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1572. Min Range: -3.1572
Max Act: 3.0153. Min Act: -0.1700
Data Index: 2135078 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1572. Min Range: -3.1572
Max Act: 2.9995. Min Act: -0.1700
Data Index: 7334481 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1572. Min Range: -3.1572
Max Act: 3.0153. Min Act: -0.1700
Data Index: 1317314 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1572. Min Range: -3.1572
Max Act: 2.9837. Min Act: -0.1700
Data Index: 6214764 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1572. Min Range: -3.1572
Max Act: 2.9837. Min Act: -0.1700
Data Index: 6396621 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1572. Min Range: -3.1572
Max Act: 2.9679. Min Act: -0.1700
Data Index: 3400646 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1572. Min Range: -3.1572
Max Act: 2.9363. Min Act: -0.1700
Data Index: 3161260 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1572. Min Range: -3.1572
Max Act: 2.9363. Min Act: -0.1700
Data Index: 8253197 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1572. Min Range: -3.1572
Max Act: 2.8887. Min Act: -0.1700
Data Index: 4405050 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1572. Min Range: -3.1572
Max Act: 2.8887. Min Act: -0.1700
Data Index: 6499436 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1572. Min Range: -3.1572
Max Act: 2.8887. Min Act: -0.1700
Data Index: 3529750 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1572. Min Range: -3.1572
Max Act: 2.8887. Min Act: -0.1700
Data Index: 2514366 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1572. Min Range: -3.1572
Max Act: 2.8728. Min Act: -0.1700
Data Index: 4593975 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1572. Min Range: -3.1572
Max Act: 2.8728. Min Act: -0.1700
Data Index: 5015571 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #19