Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4161 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1155. Min Range: -5.1155
Max Act: 5.1155. Min Act: -0.1700
Data Index: 3218168 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1155. Min Range: -5.1155
Max Act: 5.1155. Min Act: -0.1700
Data Index: 2263786 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1155. Min Range: -5.1155
Max Act: 5.0843. Min Act: -0.1700
Data Index: 649398 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1155. Min Range: -5.1155
Max Act: 5.0843. Min Act: -0.1700
Data Index: 4002843 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1155. Min Range: -5.1155
Max Act: 5.0218. Min Act: -0.1700
Data Index: 8628305 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1155. Min Range: -5.1155
Max Act: 5.0218. Min Act: -0.1700
Data Index: 8746830 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1155. Min Range: -5.1155
Max Act: 4.9905. Min Act: -0.1700
Data Index: 1852400 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1155. Min Range: -5.1155
Max Act: 4.9905. Min Act: -0.1700
Data Index: 5977380 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1155. Min Range: -5.1155
Max Act: 5.0218. Min Act: -0.1700
Data Index: 2741630 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1155. Min Range: -5.1155
Max Act: 4.9905. Min Act: -0.1700
Data Index: 4980051 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1155. Min Range: -5.1155
Max Act: 4.9905. Min Act: -0.1700
Data Index: 7096574 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1155. Min Range: -5.1155
Max Act: 4.9593. Min Act: -0.1700
Data Index: 2263779 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1155. Min Range: -5.1155
Max Act: 4.9593. Min Act: -0.1700
Data Index: 90782 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1155. Min Range: -5.1155
Max Act: 4.9593. Min Act: -0.1700
Data Index: 8066060 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1155. Min Range: -5.1155
Max Act: 4.9593. Min Act: -0.1700
Data Index: 1031413 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1155. Min Range: -5.1155
Max Act: 4.9593. Min Act: -0.1700
Data Index: 534456 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1155. Min Range: -5.1155
Max Act: 4.9280. Min Act: -0.1700
Data Index: 3866300 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1155. Min Range: -5.1155
Max Act: 4.9280. Min Act: -0.1700
Data Index: 7711779 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1155. Min Range: -5.1155
Max Act: 4.8968. Min Act: -0.1700
Data Index: 8671397 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1155. Min Range: -5.1155
Max Act: 4.8968. Min Act: -0.1700
Data Index: 783094 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #19