Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5817 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4823. Min Range: -6.4823
Max Act: 6.4823. Min Act: -0.1700
Data Index: 411778 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4823. Min Range: -6.4823
Max Act: 6.2011. Min Act: -0.1700
Data Index: 1467644 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4823. Min Range: -6.4823
Max Act: 6.2011. Min Act: -0.1700
Data Index: 5299117 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4823. Min Range: -6.4823
Max Act: 6.2011. Min Act: -0.1700
Data Index: 3581662 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4823. Min Range: -6.4823
Max Act: 6.1698. Min Act: -0.1700
Data Index: 6603903 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4823. Min Range: -6.4823
Max Act: 6.1698. Min Act: -0.1700
Data Index: 8467340 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4823. Min Range: -6.4823
Max Act: 6.1698. Min Act: -0.1700
Data Index: 2472539 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4823. Min Range: -6.4823
Max Act: 6.0136. Min Act: -0.1700
Data Index: 6495868 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4823. Min Range: -6.4823
Max Act: 6.0136. Min Act: -0.1700
Data Index: 1761270 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4823. Min Range: -6.4823
Max Act: 6.0136. Min Act: -0.1700
Data Index: 3429585 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4823. Min Range: -6.4823
Max Act: 5.9511. Min Act: -0.1700
Data Index: 8467346 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4823. Min Range: -6.4823
Max Act: 5.9198. Min Act: -0.1700
Data Index: 1727580 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4823. Min Range: -6.4823
Max Act: 5.9198. Min Act: -0.1700
Data Index: 4711582 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4823. Min Range: -6.4823
Max Act: 5.9198. Min Act: -0.1700
Data Index: 4152328 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4823. Min Range: -6.4823
Max Act: 5.8573. Min Act: -0.1700
Data Index: 6352421 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4823. Min Range: -6.4823
Max Act: 5.8886. Min Act: -0.1700
Data Index: 7354899 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4823. Min Range: -6.4823
Max Act: 5.8573. Min Act: -0.1700
Data Index: 3447202 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4823. Min Range: -6.4823
Max Act: 5.7948. Min Act: -0.1700
Data Index: 8467339 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4823. Min Range: -6.4823
Max Act: 5.7636. Min Act: -0.1700
Data Index: 1624638 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4823. Min Range: -6.4823
Max Act: 5.7636. Min Act: -0.1700
Data Index: 619401 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #19