Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2449 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7145. Min Range: -4.7145
Max Act: 4.7145. Min Act: -0.1700
Data Index: 422453 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7145. Min Range: -4.7145
Max Act: 4.7145. Min Act: -0.1700
Data Index: 3413581 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7145. Min Range: -4.7145
Max Act: 4.7145. Min Act: -0.1700
Data Index: 969826 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7145. Min Range: -4.7145
Max Act: 4.6832. Min Act: -0.1700
Data Index: 954663 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7145. Min Range: -4.7145
Max Act: 4.6832. Min Act: -0.1700
Data Index: 2327501 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7145. Min Range: -4.7145
Max Act: 4.6520. Min Act: -0.1700
Data Index: 5471060 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7145. Min Range: -4.7145
Max Act: 4.5895. Min Act: -0.1700
Data Index: 7458268 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7145. Min Range: -4.7145
Max Act: 4.6207. Min Act: -0.1700
Data Index: 4507661 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7145. Min Range: -4.7145
Max Act: 4.5895. Min Act: -0.1700
Data Index: 960247 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7145. Min Range: -4.7145
Max Act: 4.5895. Min Act: -0.1700
Data Index: 8723693 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7145. Min Range: -4.7145
Max Act: 4.5895. Min Act: -0.1700
Data Index: 6263747 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7145. Min Range: -4.7145
Max Act: 4.5895. Min Act: -0.1700
Data Index: 6058875 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7145. Min Range: -4.7145
Max Act: 4.5582. Min Act: -0.1700
Data Index: 604600 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7145. Min Range: -4.7145
Max Act: 4.5582. Min Act: -0.1700
Data Index: 4395805 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7145. Min Range: -4.7145
Max Act: 4.5582. Min Act: -0.1700
Data Index: 6061789 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7145. Min Range: -4.7145
Max Act: 4.5582. Min Act: -0.1700
Data Index: 4838064 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7145. Min Range: -4.7145
Max Act: 4.5270. Min Act: -0.1700
Data Index: 2604975 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7145. Min Range: -4.7145
Max Act: 4.5270. Min Act: -0.1700
Data Index: 5476848 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7145. Min Range: -4.7145
Max Act: 4.4957. Min Act: -0.1700
Data Index: 2668133 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7145. Min Range: -4.7145
Max Act: 4.5270. Min Act: -0.1700
Data Index: 4076682 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #19