Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 868 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1328. Min Range: -6.1328
Max Act: 6.1328. Min Act: -0.1700
Data Index: 5601183 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1328. Min Range: -6.1328
Max Act: 6.1015. Min Act: -0.1700
Data Index: 8446999 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1328. Min Range: -6.1328
Max Act: 6.0703. Min Act: -0.1700
Data Index: 700227 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1328. Min Range: -6.1328
Max Act: 6.0703. Min Act: -0.1700
Data Index: 803432 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1328. Min Range: -6.1328
Max Act: 6.0390. Min Act: -0.1700
Data Index: 8509325 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1328. Min Range: -6.1328
Max Act: 6.0390. Min Act: -0.1700
Data Index: 1242033 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1328. Min Range: -6.1328
Max Act: 6.0390. Min Act: -0.1700
Data Index: 4109807 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1328. Min Range: -6.1328
Max Act: 6.0390. Min Act: -0.1700
Data Index: 2417745 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1328. Min Range: -6.1328
Max Act: 6.0390. Min Act: -0.1700
Data Index: 3131446 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1328. Min Range: -6.1328
Max Act: 5.9765. Min Act: -0.1700
Data Index: 8527096 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1328. Min Range: -6.1328
Max Act: 6.0078. Min Act: -0.1700
Data Index: 3833757 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1328. Min Range: -6.1328
Max Act: 6.0078. Min Act: -0.1700
Data Index: 8211759 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1328. Min Range: -6.1328
Max Act: 6.0078. Min Act: -0.1700
Data Index: 3471468 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1328. Min Range: -6.1328
Max Act: 6.0078. Min Act: -0.1700
Data Index: 8715304 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1328. Min Range: -6.1328
Max Act: 6.0078. Min Act: -0.1700
Data Index: 2348452 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1328. Min Range: -6.1328
Max Act: 5.9765. Min Act: -0.1700
Data Index: 6319429 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1328. Min Range: -6.1328
Max Act: 5.9453. Min Act: -0.1700
Data Index: 8272761 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1328. Min Range: -6.1328
Max Act: 5.9453. Min Act: -0.1700
Data Index: 7201280 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1328. Min Range: -6.1328
Max Act: 5.9453. Min Act: -0.1700
Data Index: 7458938 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1328. Min Range: -6.1328
Max Act: 5.9453. Min Act: -0.1700
Data Index: 7915751 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #19