Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6218 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6797. Min Range: -4.6797
Max Act: 4.6797. Min Act: -0.1700
Data Index: 6183708 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6797. Min Range: -4.6797
Max Act: 4.6485. Min Act: -0.1700
Data Index: 6215469 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6797. Min Range: -4.6797
Max Act: 4.6172. Min Act: -0.1700
Data Index: 8278285 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6797. Min Range: -4.6797
Max Act: 4.6172. Min Act: -0.1700
Data Index: 3870925 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6797. Min Range: -4.6797
Max Act: 4.5860. Min Act: -0.1700
Data Index: 226190 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6797. Min Range: -4.6797
Max Act: 4.5235. Min Act: -0.1700
Data Index: 3842943 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6797. Min Range: -4.6797
Max Act: 4.5235. Min Act: -0.1700
Data Index: 5376271 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6797. Min Range: -4.6797
Max Act: 4.5235. Min Act: -0.1700
Data Index: 8158635 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6797. Min Range: -4.6797
Max Act: 4.4922. Min Act: -0.1700
Data Index: 7020609 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6797. Min Range: -4.6797
Max Act: 4.4922. Min Act: -0.1700
Data Index: 644223 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6797. Min Range: -4.6797
Max Act: 4.4922. Min Act: -0.1700
Data Index: 6362919 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6797. Min Range: -4.6797
Max Act: 4.4922. Min Act: -0.1700
Data Index: 4988832 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6797. Min Range: -4.6797
Max Act: 4.4922. Min Act: -0.1700
Data Index: 3479525 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6797. Min Range: -4.6797
Max Act: 4.4922. Min Act: -0.1700
Data Index: 8488132 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6797. Min Range: -4.6797
Max Act: 4.4922. Min Act: -0.1700
Data Index: 7579672 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6797. Min Range: -4.6797
Max Act: 4.4610. Min Act: -0.1700
Data Index: 8095512 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6797. Min Range: -4.6797
Max Act: 4.4610. Min Act: -0.1700
Data Index: 4003927 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6797. Min Range: -4.6797
Max Act: 4.4610. Min Act: -0.1700
Data Index: 4964935 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6797. Min Range: -4.6797
Max Act: 4.4297. Min Act: -0.1700
Data Index: 1263257 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6797. Min Range: -4.6797
Max Act: 4.4297. Min Act: -0.1700
Data Index: 817198 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #19