Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2472 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1408. Min Range: -4.1408
Max Act: 4.1408. Min Act: -0.1700
Data Index: 527850 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1408. Min Range: -4.1408
Max Act: 4.0783. Min Act: -0.1700
Data Index: 7717060 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1408. Min Range: -4.1408
Max Act: 4.0470. Min Act: -0.1700
Data Index: 593628 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1408. Min Range: -4.1408
Max Act: 3.9532. Min Act: -0.1700
Data Index: 6113760 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1408. Min Range: -4.1408
Max Act: 3.9532. Min Act: -0.1700
Data Index: 1741412 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1408. Min Range: -4.1408
Max Act: 3.9220. Min Act: -0.1700
Data Index: 444542 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1408. Min Range: -4.1408
Max Act: 3.8907. Min Act: -0.1700
Data Index: 5339889 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1408. Min Range: -4.1408
Max Act: 3.8282. Min Act: -0.1700
Data Index: 2816299 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1408. Min Range: -4.1408
Max Act: 3.7969. Min Act: -0.1700
Data Index: 846434 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1408. Min Range: -4.1408
Max Act: 3.7813. Min Act: -0.1700
Data Index: 3201206 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1408. Min Range: -4.1408
Max Act: 3.7813. Min Act: -0.1700
Data Index: 8092629 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1408. Min Range: -4.1408
Max Act: 3.7656. Min Act: -0.1700
Data Index: 4419609 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1408. Min Range: -4.1408
Max Act: 3.7500. Min Act: -0.1700
Data Index: 3790176 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1408. Min Range: -4.1408
Max Act: 3.7343. Min Act: -0.1700
Data Index: 2748919 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1408. Min Range: -4.1408
Max Act: 3.7500. Min Act: -0.1700
Data Index: 7407142 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1408. Min Range: -4.1408
Max Act: 3.7500. Min Act: -0.1700
Data Index: 8789683 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1408. Min Range: -4.1408
Max Act: 3.6874. Min Act: -0.1700
Data Index: 1017658 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1408. Min Range: -4.1408
Max Act: 3.7031. Min Act: -0.1700
Data Index: 7958121 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1408. Min Range: -4.1408
Max Act: 3.7031. Min Act: -0.1700
Data Index: 57538 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1408. Min Range: -4.1408
Max Act: 3.7031. Min Act: -0.1700
Data Index: 4260343 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #19