Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3169 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2211. Min Range: -5.2211
Max Act: 5.2211. Min Act: -0.1700
Data Index: 2514000 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2211. Min Range: -5.2211
Max Act: 4.8461. Min Act: -0.1700
Data Index: 4375763 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2211. Min Range: -5.2211
Max Act: 4.8148. Min Act: -0.1700
Data Index: 565105 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2211. Min Range: -5.2211
Max Act: 4.7211. Min Act: -0.1700
Data Index: 5631357 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2211. Min Range: -5.2211
Max Act: 4.6586. Min Act: -0.1700
Data Index: 5568993 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2211. Min Range: -5.2211
Max Act: 4.6273. Min Act: -0.1700
Data Index: 4256725 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2211. Min Range: -5.2211
Max Act: 4.6273. Min Act: -0.1700
Data Index: 1743317 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2211. Min Range: -5.2211
Max Act: 4.6586. Min Act: -0.1700
Data Index: 4375764 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2211. Min Range: -5.2211
Max Act: 4.6273. Min Act: -0.1700
Data Index: 6778170 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2211. Min Range: -5.2211
Max Act: 4.6273. Min Act: -0.1700
Data Index: 4222143 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2211. Min Range: -5.2211
Max Act: 4.5961. Min Act: -0.1700
Data Index: 2574624 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2211. Min Range: -5.2211
Max Act: 4.5961. Min Act: -0.1700
Data Index: 4226328 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2211. Min Range: -5.2211
Max Act: 4.5648. Min Act: -0.1700
Data Index: 5758968 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2211. Min Range: -5.2211
Max Act: 4.5648. Min Act: -0.1700
Data Index: 8809522 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2211. Min Range: -5.2211
Max Act: 4.5648. Min Act: -0.1700
Data Index: 8114428 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2211. Min Range: -5.2211
Max Act: 4.5023. Min Act: -0.1700
Data Index: 7796794 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2211. Min Range: -5.2211
Max Act: 4.5023. Min Act: -0.1700
Data Index: 3974885 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2211. Min Range: -5.2211
Max Act: 4.5023. Min Act: -0.1700
Data Index: 5767711 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2211. Min Range: -5.2211
Max Act: 4.5023. Min Act: -0.1700
Data Index: 2527313 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2211. Min Range: -5.2211
Max Act: 4.4711. Min Act: -0.1700
Data Index: 856897 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #19