Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3475 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9190. Min Range: -6.9190
Max Act: 6.9190. Min Act: -0.1700
Data Index: 1935513 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9190. Min Range: -6.9190
Max Act: 6.6377. Min Act: -0.1700
Data Index: 3792212 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9190. Min Range: -6.9190
Max Act: 6.6065. Min Act: -0.1700
Data Index: 1325219 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9190. Min Range: -6.9190
Max Act: 6.5127. Min Act: -0.1700
Data Index: 8429327 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9190. Min Range: -6.9190
Max Act: 6.5127. Min Act: -0.1700
Data Index: 8526767 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9190. Min Range: -6.9190
Max Act: 6.5127. Min Act: -0.1700
Data Index: 3227976 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9190. Min Range: -6.9190
Max Act: 6.4815. Min Act: -0.1700
Data Index: 6269755 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9190. Min Range: -6.9190
Max Act: 6.4815. Min Act: -0.1700
Data Index: 3349695 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9190. Min Range: -6.9190
Max Act: 6.4815. Min Act: -0.1700
Data Index: 1312588 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9190. Min Range: -6.9190
Max Act: 6.4815. Min Act: -0.1700
Data Index: 61702 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9190. Min Range: -6.9190
Max Act: 6.4502. Min Act: -0.1700
Data Index: 1633080 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9190. Min Range: -6.9190
Max Act: 6.4190. Min Act: -0.1700
Data Index: 7393528 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9190. Min Range: -6.9190
Max Act: 6.4502. Min Act: -0.1700
Data Index: 3725549 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9190. Min Range: -6.9190
Max Act: 6.4190. Min Act: -0.1700
Data Index: 4777876 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9190. Min Range: -6.9190
Max Act: 6.3877. Min Act: -0.1700
Data Index: 4819274 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9190. Min Range: -6.9190
Max Act: 6.3877. Min Act: -0.1700
Data Index: 839241 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9190. Min Range: -6.9190
Max Act: 6.3877. Min Act: -0.1700
Data Index: 5001191 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9190. Min Range: -6.9190
Max Act: 6.3565. Min Act: -0.1700
Data Index: 4579217 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9190. Min Range: -6.9190
Max Act: 6.3565. Min Act: -0.1700
Data Index: 2773233 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9190. Min Range: -6.9190
Max Act: 6.3565. Min Act: -0.1700
Data Index: 5908043 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #19