Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1020 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5680. Min Range: -4.5680
Max Act: 4.5680. Min Act: -0.1700
Data Index: 608752 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5680. Min Range: -4.5680
Max Act: 4.4743. Min Act: -0.1700
Data Index: 4245071 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5680. Min Range: -4.5680
Max Act: 4.4430. Min Act: -0.1700
Data Index: 4526944 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5680. Min Range: -4.5680
Max Act: 4.4430. Min Act: -0.1700
Data Index: 7458743 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5680. Min Range: -4.5680
Max Act: 4.4118. Min Act: -0.1700
Data Index: 6576306 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5680. Min Range: -4.5680
Max Act: 4.4118. Min Act: -0.1700
Data Index: 5987039 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5680. Min Range: -4.5680
Max Act: 4.4118. Min Act: -0.1700
Data Index: 8253107 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5680. Min Range: -4.5680
Max Act: 4.3180. Min Act: -0.1700
Data Index: 5819728 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5680. Min Range: -4.5680
Max Act: 4.2868. Min Act: -0.1700
Data Index: 3292126 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5680. Min Range: -4.5680
Max Act: 4.2868. Min Act: -0.1700
Data Index: 5603662 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5680. Min Range: -4.5680
Max Act: 4.2868. Min Act: -0.1700
Data Index: 2070730 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5680. Min Range: -4.5680
Max Act: 4.2868. Min Act: -0.1700
Data Index: 8613849 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5680. Min Range: -4.5680
Max Act: 4.2868. Min Act: -0.1700
Data Index: 1227045 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5680. Min Range: -4.5680
Max Act: 4.2555. Min Act: -0.1700
Data Index: 3098626 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5680. Min Range: -4.5680
Max Act: 4.2555. Min Act: -0.1700
Data Index: 6278025 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5680. Min Range: -4.5680
Max Act: 4.1930. Min Act: -0.1700
Data Index: 2363347 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5680. Min Range: -4.5680
Max Act: 4.2243. Min Act: -0.1700
Data Index: 7724212 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5680. Min Range: -4.5680
Max Act: 4.2243. Min Act: -0.1700
Data Index: 1120230 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5680. Min Range: -4.5680
Max Act: 4.2243. Min Act: -0.1700
Data Index: 3693179 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5680. Min Range: -4.5680
Max Act: 4.2243. Min Act: -0.1700
Data Index: 1301203 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #19