Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1226 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8727. Min Range: -6.8727
Max Act: 6.8727. Min Act: -0.1693
Data Index: 596448 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8727. Min Range: -6.8727
Max Act: 6.8727. Min Act: -0.1700
Data Index: 406778 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8727. Min Range: -6.8727
Max Act: 6.8415. Min Act: -0.1700
Data Index: 3548372 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8727. Min Range: -6.8727
Max Act: 6.8102. Min Act: -0.1700
Data Index: 425743 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8727. Min Range: -6.8727
Max Act: 6.6540. Min Act: -0.1700
Data Index: 2818249 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8727. Min Range: -6.8727
Max Act: 6.6540. Min Act: -0.1700
Data Index: 4059156 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8727. Min Range: -6.8727
Max Act: 6.6540. Min Act: -0.1700
Data Index: 10173 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8727. Min Range: -6.8727
Max Act: 6.5915. Min Act: -0.1700
Data Index: 6943454 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8727. Min Range: -6.8727
Max Act: 6.5915. Min Act: -0.1700
Data Index: 1062409 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8727. Min Range: -6.8727
Max Act: 6.5290. Min Act: -0.1700
Data Index: 1773229 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8727. Min Range: -6.8727
Max Act: 6.5290. Min Act: -0.1700
Data Index: 3214079 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8727. Min Range: -6.8727
Max Act: 6.4977. Min Act: -0.1700
Data Index: 1680940 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8727. Min Range: -6.8727
Max Act: 6.4977. Min Act: -0.1684
Data Index: 5460447 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8727. Min Range: -6.8727
Max Act: 6.4977. Min Act: -0.1700
Data Index: 2288687 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8727. Min Range: -6.8727
Max Act: 6.4665. Min Act: -0.1700
Data Index: 1680938 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8727. Min Range: -6.8727
Max Act: 6.4665. Min Act: -0.1700
Data Index: 7578265 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8727. Min Range: -6.8727
Max Act: 6.4665. Min Act: -0.1700
Data Index: 7471895 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8727. Min Range: -6.8727
Max Act: 6.4665. Min Act: -0.1700
Data Index: 895082 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8727. Min Range: -6.8727
Max Act: 6.4665. Min Act: -0.1700
Data Index: 1661090 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8727. Min Range: -6.8727
Max Act: 6.4352. Min Act: -0.1700
Data Index: 2574629 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #19