Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 929 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2899. Min Range: -3.2899
Max Act: 3.2899. Min Act: -0.1700
Data Index: 7376278 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2899. Min Range: -3.2899
Max Act: 3.2742. Min Act: -0.1700
Data Index: 8678810 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2899. Min Range: -3.2899
Max Act: 3.2585. Min Act: -0.1700
Data Index: 1648541 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2899. Min Range: -3.2899
Max Act: 3.2428. Min Act: -0.1700
Data Index: 1979117 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2899. Min Range: -3.2899
Max Act: 3.2428. Min Act: -0.1700
Data Index: 8144390 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2899. Min Range: -3.2899
Max Act: 3.2271. Min Act: -0.1700
Data Index: 228814 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2899. Min Range: -3.2899
Max Act: 3.2114. Min Act: -0.1700
Data Index: 2981693 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2899. Min Range: -3.2899
Max Act: 3.2114. Min Act: -0.1700
Data Index: 8096706 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2899. Min Range: -3.2899
Max Act: 3.2114. Min Act: -0.1700
Data Index: 7063920 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2899. Min Range: -3.2899
Max Act: 3.1957. Min Act: -0.1700
Data Index: 5242609 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2899. Min Range: -3.2899
Max Act: 3.1957. Min Act: -0.1700
Data Index: 4738 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2899. Min Range: -3.2899
Max Act: 3.1957. Min Act: -0.1700
Data Index: 1127328 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2899. Min Range: -3.2899
Max Act: 3.1799. Min Act: -0.1700
Data Index: 2016825 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2899. Min Range: -3.2899
Max Act: 3.1799. Min Act: -0.1700
Data Index: 4332471 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2899. Min Range: -3.2899
Max Act: 3.1799. Min Act: -0.1700
Data Index: 4159861 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2899. Min Range: -3.2899
Max Act: 3.1799. Min Act: -0.1700
Data Index: 406808 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2899. Min Range: -3.2899
Max Act: 3.1799. Min Act: -0.1700
Data Index: 3795477 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2899. Min Range: -3.2899
Max Act: 3.1799. Min Act: -0.1700
Data Index: 7914527 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2899. Min Range: -3.2899
Max Act: 3.1799. Min Act: -0.1700
Data Index: 1892272 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2899. Min Range: -3.2899
Max Act: 3.1799. Min Act: -0.1700
Data Index: 7143009 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19