Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3001 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6255. Min Range: -6.6255
Max Act: 6.6255. Min Act: -0.1700
Data Index: 6889858 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6255. Min Range: -6.6255
Max Act: 6.4068. Min Act: -0.1700
Data Index: 8007400 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6255. Min Range: -6.6255
Max Act: 6.3755. Min Act: -0.1700
Data Index: 3062195 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6255. Min Range: -6.6255
Max Act: 6.2505. Min Act: -0.1700
Data Index: 2437468 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6255. Min Range: -6.6255
Max Act: 6.2193. Min Act: -0.1700
Data Index: 6552208 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6255. Min Range: -6.6255
Max Act: 6.2193. Min Act: -0.1700
Data Index: 6610156 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6255. Min Range: -6.6255
Max Act: 6.2193. Min Act: -0.1700
Data Index: 3668742 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6255. Min Range: -6.6255
Max Act: 6.1880. Min Act: -0.1700
Data Index: 7573844 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6255. Min Range: -6.6255
Max Act: 6.1568. Min Act: -0.1700
Data Index: 5579287 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6255. Min Range: -6.6255
Max Act: 6.1880. Min Act: -0.1700
Data Index: 39962 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6255. Min Range: -6.6255
Max Act: 6.1255. Min Act: -0.1700
Data Index: 7171482 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6255. Min Range: -6.6255
Max Act: 6.1568. Min Act: -0.1700
Data Index: 1217952 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6255. Min Range: -6.6255
Max Act: 6.1255. Min Act: -0.1700
Data Index: 3163860 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6255. Min Range: -6.6255
Max Act: 6.1255. Min Act: -0.1700
Data Index: 1192292 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6255. Min Range: -6.6255
Max Act: 6.0630. Min Act: -0.1700
Data Index: 2557589 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6255. Min Range: -6.6255
Max Act: 6.0943. Min Act: -0.1700
Data Index: 3597527 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6255. Min Range: -6.6255
Max Act: 6.0943. Min Act: -0.1700
Data Index: 2654600 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6255. Min Range: -6.6255
Max Act: 6.0318. Min Act: -0.1700
Data Index: 2890078 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6255. Min Range: -6.6255
Max Act: 6.0630. Min Act: -0.1700
Data Index: 2055016 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6255. Min Range: -6.6255
Max Act: 6.0630. Min Act: -0.1700
Data Index: 3570020 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #19