Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3606 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1874. Min Range: -5.1874
Max Act: 5.1874. Min Act: -0.1700
Data Index: 7120404 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1874. Min Range: -5.1874
Max Act: 5.1249. Min Act: -0.1700
Data Index: 6853449 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1874. Min Range: -5.1874
Max Act: 5.1561. Min Act: -0.1700
Data Index: 594007 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1874. Min Range: -5.1874
Max Act: 5.0936. Min Act: -0.1700
Data Index: 1460326 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1874. Min Range: -5.1874
Max Act: 5.0624. Min Act: -0.1700
Data Index: 4461859 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1874. Min Range: -5.1874
Max Act: 5.0624. Min Act: -0.1700
Data Index: 5742597 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1874. Min Range: -5.1874
Max Act: 4.9999. Min Act: -0.1700
Data Index: 5332552 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1874. Min Range: -5.1874
Max Act: 4.9686. Min Act: -0.1700
Data Index: 6744537 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1874. Min Range: -5.1874
Max Act: 4.9686. Min Act: -0.1700
Data Index: 1409879 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1874. Min Range: -5.1874
Max Act: 4.9686. Min Act: -0.1700
Data Index: 7474695 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1874. Min Range: -5.1874
Max Act: 4.9686. Min Act: -0.1700
Data Index: 3579162 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1874. Min Range: -5.1874
Max Act: 4.9686. Min Act: -0.1700
Data Index: 4690333 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1874. Min Range: -5.1874
Max Act: 4.9686. Min Act: -0.1700
Data Index: 68604 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1874. Min Range: -5.1874
Max Act: 4.9686. Min Act: -0.1700
Data Index: 7474694 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1874. Min Range: -5.1874
Max Act: 4.9374. Min Act: -0.1700
Data Index: 4900760 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1874. Min Range: -5.1874
Max Act: 4.9374. Min Act: -0.1700
Data Index: 7362768 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1874. Min Range: -5.1874
Max Act: 4.9374. Min Act: -0.1700
Data Index: 2690335 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1874. Min Range: -5.1874
Max Act: 4.9061. Min Act: -0.1700
Data Index: 495893 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1874. Min Range: -5.1874
Max Act: 4.9061. Min Act: -0.1700
Data Index: 4362372 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1874. Min Range: -5.1874
Max Act: 4.9061. Min Act: -0.1700
Data Index: 2375312 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #19