Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 392 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6394. Min Range: -5.6394
Max Act: 5.6394. Min Act: -0.1700
Data Index: 2019223 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6394. Min Range: -5.6394
Max Act: 5.5769. Min Act: -0.1700
Data Index: 4839355 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6394. Min Range: -5.6394
Max Act: 5.5457. Min Act: -0.1700
Data Index: 2903581 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6394. Min Range: -5.6394
Max Act: 5.4832. Min Act: -0.1700
Data Index: 5202209 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6394. Min Range: -5.6394
Max Act: 5.4519. Min Act: -0.1700
Data Index: 6201021 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6394. Min Range: -5.6394
Max Act: 5.4519. Min Act: -0.1700
Data Index: 7744308 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6394. Min Range: -5.6394
Max Act: 5.4207. Min Act: -0.1700
Data Index: 193640 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6394. Min Range: -5.6394
Max Act: 5.3894. Min Act: -0.1700
Data Index: 8522256 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6394. Min Range: -5.6394
Max Act: 5.3894. Min Act: -0.1700
Data Index: 228313 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6394. Min Range: -5.6394
Max Act: 5.3894. Min Act: -0.1700
Data Index: 2019216 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6394. Min Range: -5.6394
Max Act: 5.4207. Min Act: -0.1700
Data Index: 6843629 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6394. Min Range: -5.6394
Max Act: 5.3582. Min Act: -0.1700
Data Index: 2480558 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6394. Min Range: -5.6394
Max Act: 5.3582. Min Act: -0.1700
Data Index: 4864099 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6394. Min Range: -5.6394
Max Act: 5.3269. Min Act: -0.1700
Data Index: 3350055 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6394. Min Range: -5.6394
Max Act: 5.3269. Min Act: -0.1700
Data Index: 8684195 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6394. Min Range: -5.6394
Max Act: 5.2644. Min Act: -0.1700
Data Index: 2846393 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6394. Min Range: -5.6394
Max Act: 5.2957. Min Act: -0.1700
Data Index: 6236866 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6394. Min Range: -5.6394
Max Act: 5.2957. Min Act: -0.1700
Data Index: 1431699 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6394. Min Range: -5.6394
Max Act: 5.2644. Min Act: -0.1700
Data Index: 7036844 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6394. Min Range: -5.6394
Max Act: 5.2644. Min Act: -0.1700
Data Index: 1644438 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #19