Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5555 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1492. Min Range: -5.1492
Max Act: 5.1492. Min Act: -0.1700
Data Index: 4244832 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1492. Min Range: -5.1492
Max Act: 5.1179. Min Act: -0.1700
Data Index: 1548808 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1492. Min Range: -5.1492
Max Act: 5.0867. Min Act: -0.1700
Data Index: 6409904 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1492. Min Range: -5.1492
Max Act: 5.0867. Min Act: -0.1700
Data Index: 4932611 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1492. Min Range: -5.1492
Max Act: 5.0554. Min Act: -0.1700
Data Index: 6096305 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1492. Min Range: -5.1492
Max Act: 5.0242. Min Act: -0.1700
Data Index: 843572 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1492. Min Range: -5.1492
Max Act: 5.0242. Min Act: -0.1700
Data Index: 8559912 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1492. Min Range: -5.1492
Max Act: 4.9929. Min Act: -0.1700
Data Index: 8118742 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1492. Min Range: -5.1492
Max Act: 4.9617. Min Act: -0.1700
Data Index: 6823630 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1492. Min Range: -5.1492
Max Act: 4.9617. Min Act: -0.1700
Data Index: 5164688 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1492. Min Range: -5.1492
Max Act: 4.9929. Min Act: -0.1700
Data Index: 8321973 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1492. Min Range: -5.1492
Max Act: 4.9617. Min Act: -0.1700
Data Index: 8427978 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1492. Min Range: -5.1492
Max Act: 4.9304. Min Act: -0.1700
Data Index: 1216408 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1492. Min Range: -5.1492
Max Act: 4.9304. Min Act: -0.1700
Data Index: 5885413 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1492. Min Range: -5.1492
Max Act: 4.9304. Min Act: -0.1700
Data Index: 5885404 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1492. Min Range: -5.1492
Max Act: 4.9304. Min Act: -0.1700
Data Index: 8304016 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1492. Min Range: -5.1492
Max Act: 4.9304. Min Act: -0.1700
Data Index: 2341214 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1492. Min Range: -5.1492
Max Act: 4.9304. Min Act: -0.1700
Data Index: 7217869 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1492. Min Range: -5.1492
Max Act: 4.9304. Min Act: -0.1700
Data Index: 5885410 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1492. Min Range: -5.1492
Max Act: 4.9617. Min Act: -0.1700
Data Index: 4262813 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #19