Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5348 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2773. Min Range: -4.2773
Max Act: 4.2773. Min Act: -0.1700
Data Index: 5528807 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2773. Min Range: -4.2773
Max Act: 4.2460. Min Act: -0.1700
Data Index: 5393267 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2773. Min Range: -4.2773
Max Act: 4.2460. Min Act: -0.1700
Data Index: 5526239 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2773. Min Range: -4.2773
Max Act: 4.2460. Min Act: -0.1700
Data Index: 7443263 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2773. Min Range: -4.2773
Max Act: 4.2460. Min Act: -0.1700
Data Index: 1246431 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2773. Min Range: -4.2773
Max Act: 4.2460. Min Act: -0.1700
Data Index: 4075576 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2773. Min Range: -4.2773
Max Act: 4.2460. Min Act: -0.1700
Data Index: 1176983 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2773. Min Range: -4.2773
Max Act: 4.2148. Min Act: -0.1700
Data Index: 5088272 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2773. Min Range: -4.2773
Max Act: 4.2148. Min Act: -0.1700
Data Index: 4689778 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2773. Min Range: -4.2773
Max Act: 4.2148. Min Act: -0.1700
Data Index: 115469 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2773. Min Range: -4.2773
Max Act: 4.2148. Min Act: -0.1700
Data Index: 1761837 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2773. Min Range: -4.2773
Max Act: 4.2148. Min Act: -0.1700
Data Index: 1204050 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2773. Min Range: -4.2773
Max Act: 4.2148. Min Act: -0.1700
Data Index: 1709537 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2773. Min Range: -4.2773
Max Act: 4.2148. Min Act: -0.1700
Data Index: 1030588 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2773. Min Range: -4.2773
Max Act: 4.2148. Min Act: -0.1700
Data Index: 558191 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2773. Min Range: -4.2773
Max Act: 4.2148. Min Act: -0.1700
Data Index: 4634317 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2773. Min Range: -4.2773
Max Act: 4.1835. Min Act: -0.1700
Data Index: 1486838 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2773. Min Range: -4.2773
Max Act: 4.2148. Min Act: -0.1700
Data Index: 4104106 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2773. Min Range: -4.2773
Max Act: 4.2148. Min Act: -0.1700
Data Index: 3798572 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2773. Min Range: -4.2773
Max Act: 4.2148. Min Act: -0.1700
Data Index: 3253063 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19