Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3641 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1993. Min Range: -6.1993
Max Act: 6.1993. Min Act: -0.1700
Data Index: 1005650 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1993. Min Range: -6.1993
Max Act: 6.1993. Min Act: -0.1700
Data Index: 4668025 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1993. Min Range: -6.1993
Max Act: 6.0743. Min Act: -0.1700
Data Index: 935653 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1993. Min Range: -6.1993
Max Act: 6.0743. Min Act: -0.1700
Data Index: 1900935 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1993. Min Range: -6.1993
Max Act: 5.8555. Min Act: -0.1700
Data Index: 6815732 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1993. Min Range: -6.1993
Max Act: 5.8243. Min Act: -0.1700
Data Index: 2066546 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1993. Min Range: -6.1993
Max Act: 5.7618. Min Act: -0.1700
Data Index: 418842 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1993. Min Range: -6.1993
Max Act: 5.7305. Min Act: -0.1700
Data Index: 3220086 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1993. Min Range: -6.1993
Max Act: 5.6993. Min Act: -0.1700
Data Index: 7816205 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1993. Min Range: -6.1993
Max Act: 5.6993. Min Act: -0.1700
Data Index: 7211416 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1993. Min Range: -6.1993
Max Act: 5.6680. Min Act: -0.1700
Data Index: 7119147 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1993. Min Range: -6.1993
Max Act: 5.6368. Min Act: -0.1700
Data Index: 2373888 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1993. Min Range: -6.1993
Max Act: 5.6368. Min Act: -0.1700
Data Index: 974394 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1993. Min Range: -6.1993
Max Act: 5.6368. Min Act: -0.1700
Data Index: 1896146 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1993. Min Range: -6.1993
Max Act: 5.6055. Min Act: -0.1700
Data Index: 3543984 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1993. Min Range: -6.1993
Max Act: 5.6055. Min Act: -0.1700
Data Index: 7519625 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1993. Min Range: -6.1993
Max Act: 5.6055. Min Act: -0.1700
Data Index: 3212255 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1993. Min Range: -6.1993
Max Act: 5.5743. Min Act: -0.1700
Data Index: 7807595 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1993. Min Range: -6.1993
Max Act: 5.5118. Min Act: -0.1700
Data Index: 3819738 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1993. Min Range: -6.1993
Max Act: 5.5430. Min Act: -0.1700
Data Index: 2640333 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #19