Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4670 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3704. Min Range: -6.3704
Max Act: 6.3704. Min Act: -0.1700
Data Index: 645611 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3704. Min Range: -6.3704
Max Act: 6.1204. Min Act: -0.1700
Data Index: 2076251 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3704. Min Range: -6.3704
Max Act: 6.1204. Min Act: -0.1700
Data Index: 2185793 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3704. Min Range: -6.3704
Max Act: 6.0891. Min Act: -0.1700
Data Index: 1088578 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3704. Min Range: -6.3704
Max Act: 6.0891. Min Act: -0.1700
Data Index: 413701 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3704. Min Range: -6.3704
Max Act: 6.0579. Min Act: -0.1700
Data Index: 5349744 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3704. Min Range: -6.3704
Max Act: 6.0891. Min Act: -0.1700
Data Index: 976751 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3704. Min Range: -6.3704
Max Act: 6.0579. Min Act: -0.1700
Data Index: 8585966 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3704. Min Range: -6.3704
Max Act: 6.0891. Min Act: -0.1700
Data Index: 2848722 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3704. Min Range: -6.3704
Max Act: 6.0579. Min Act: -0.1700
Data Index: 8585968 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3704. Min Range: -6.3704
Max Act: 5.9954. Min Act: -0.1700
Data Index: 2847714 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3704. Min Range: -6.3704
Max Act: 6.0266. Min Act: -0.1700
Data Index: 6814400 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3704. Min Range: -6.3704
Max Act: 6.0266. Min Act: -0.1700
Data Index: 7876624 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3704. Min Range: -6.3704
Max Act: 6.0266. Min Act: -0.1700
Data Index: 7429215 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3704. Min Range: -6.3704
Max Act: 6.0266. Min Act: -0.1700
Data Index: 1719334 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3704. Min Range: -6.3704
Max Act: 5.9954. Min Act: -0.1700
Data Index: 1981240 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3704. Min Range: -6.3704
Max Act: 5.9641. Min Act: -0.1700
Data Index: 1804710 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3704. Min Range: -6.3704
Max Act: 5.9641. Min Act: -0.1700
Data Index: 8328645 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3704. Min Range: -6.3704
Max Act: 5.9329. Min Act: -0.1700
Data Index: 8483859 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3704. Min Range: -6.3704
Max Act: 5.9329. Min Act: -0.1700
Data Index: 795607 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #19