Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2812 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1590. Min Range: -5.1590
Max Act: 5.1590. Min Act: -0.1700
Data Index: 1098369 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1590. Min Range: -5.1590
Max Act: 4.9715. Min Act: -0.1700
Data Index: 2010970 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1590. Min Range: -5.1590
Max Act: 4.8778. Min Act: -0.1700
Data Index: 7931332 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1590. Min Range: -5.1590
Max Act: 4.8153. Min Act: -0.1700
Data Index: 4924364 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1590. Min Range: -5.1590
Max Act: 4.8153. Min Act: -0.1700
Data Index: 5826679 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1590. Min Range: -5.1590
Max Act: 4.8153. Min Act: -0.1700
Data Index: 5351253 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1590. Min Range: -5.1590
Max Act: 4.8465. Min Act: -0.1700
Data Index: 6540090 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1590. Min Range: -5.1590
Max Act: 4.7840. Min Act: -0.1700
Data Index: 2281157 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1590. Min Range: -5.1590
Max Act: 4.7840. Min Act: -0.1700
Data Index: 4837144 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1590. Min Range: -5.1590
Max Act: 4.7528. Min Act: -0.1700
Data Index: 7890919 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1590. Min Range: -5.1590
Max Act: 4.7528. Min Act: -0.1700
Data Index: 3599509 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1590. Min Range: -5.1590
Max Act: 4.7215. Min Act: -0.1700
Data Index: 5857714 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1590. Min Range: -5.1590
Max Act: 4.7528. Min Act: -0.1700
Data Index: 946448 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1590. Min Range: -5.1590
Max Act: 4.7215. Min Act: -0.1700
Data Index: 1993649 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1590. Min Range: -5.1590
Max Act: 4.6903. Min Act: -0.1700
Data Index: 8461395 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1590. Min Range: -5.1590
Max Act: 4.6590. Min Act: -0.1700
Data Index: 4933461 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1590. Min Range: -5.1590
Max Act: 4.6903. Min Act: -0.1700
Data Index: 569630 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1590. Min Range: -5.1590
Max Act: 4.6590. Min Act: -0.1700
Data Index: 7470675 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1590. Min Range: -5.1590
Max Act: 4.6903. Min Act: -0.1700
Data Index: 5817680 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1590. Min Range: -5.1590
Max Act: 4.6903. Min Act: -0.1700
Data Index: 5695736 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #19