Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1870 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 0.9673. Min Range: -0.9673
Max Act: 0.9673. Min Act: -0.1700
Data Index: 3983382 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.9673. Min Range: -0.9673
Max Act: 0.9415. Min Act: -0.1700
Data Index: 798986 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.9673. Min Range: -0.9673
Max Act: 0.9157. Min Act: -0.1700
Data Index: 3903209 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.9673. Min Range: -0.9673
Max Act: 0.8985. Min Act: -0.1700
Data Index: 1881088 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.9673. Min Range: -0.9673
Max Act: 0.8900. Min Act: -0.1700
Data Index: 5838758 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.9673. Min Range: -0.9673
Max Act: 0.8729. Min Act: -0.1700
Data Index: 838219 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.9673. Min Range: -0.9673
Max Act: 0.8644. Min Act: -0.1700
Data Index: 5913649 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.9673. Min Range: -0.9673
Max Act: 0.8475. Min Act: -0.1700
Data Index: 2160301 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.9673. Min Range: -0.9673
Max Act: 0.8390. Min Act: -0.1700
Data Index: 4629354 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.9673. Min Range: -0.9673
Max Act: 0.8475. Min Act: -0.1700
Data Index: 4648097 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.9673. Min Range: -0.9673
Max Act: 0.8475. Min Act: -0.1700
Data Index: 5109799 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.9673. Min Range: -0.9673
Max Act: 0.8475. Min Act: -0.1700
Data Index: 5477747 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.9673. Min Range: -0.9673
Max Act: 0.8475. Min Act: -0.1700
Data Index: 4361064 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.9673. Min Range: -0.9673
Max Act: 0.8390. Min Act: -0.1700
Data Index: 800227 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.9673. Min Range: -0.9673
Max Act: 0.8306. Min Act: -0.1700
Data Index: 6988179 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.9673. Min Range: -0.9673
Max Act: 0.8306. Min Act: -0.1700
Data Index: 7790978 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.9673. Min Range: -0.9673
Max Act: 0.8221. Min Act: -0.1700
Data Index: 3563973 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.9673. Min Range: -0.9673
Max Act: 0.8221. Min Act: -0.1700
Data Index: 6147182 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.9673. Min Range: -0.9673
Max Act: 0.8221. Min Act: -0.1700
Data Index: 3838 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.9673. Min Range: -0.9673
Max Act: 0.8221. Min Act: -0.1700
Data Index: 2596364 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #19