Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3510 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.4604. Min Range: -6.4604
Max Act: 6.4604. Min Act: -0.1700
Data Index: 1526799 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4604. Min Range: -6.4604
Max Act: 6.4292. Min Act: -0.1700
Data Index: 4992158 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4604. Min Range: -6.4604
Max Act: 6.3979. Min Act: -0.1700
Data Index: 3903960 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4604. Min Range: -6.4604
Max Act: 6.3667. Min Act: -0.1700
Data Index: 5487693 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4604. Min Range: -6.4604
Max Act: 6.3667. Min Act: -0.1700
Data Index: 3506886 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4604. Min Range: -6.4604
Max Act: 6.2104. Min Act: -0.1700
Data Index: 2196525 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4604. Min Range: -6.4604
Max Act: 6.1792. Min Act: -0.1700
Data Index: 8092496 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4604. Min Range: -6.4604
Max Act: 6.1479. Min Act: -0.1700
Data Index: 4389165 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4604. Min Range: -6.4604
Max Act: 6.1479. Min Act: -0.1700
Data Index: 7631675 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4604. Min Range: -6.4604
Max Act: 6.1167. Min Act: -0.1700
Data Index: 3003104 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4604. Min Range: -6.4604
Max Act: 6.1167. Min Act: -0.1700
Data Index: 1693175 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4604. Min Range: -6.4604
Max Act: 6.0542. Min Act: -0.1700
Data Index: 5854682 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4604. Min Range: -6.4604
Max Act: 6.0854. Min Act: -0.1700
Data Index: 1246003 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4604. Min Range: -6.4604
Max Act: 6.0229. Min Act: -0.1700
Data Index: 1748419 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4604. Min Range: -6.4604
Max Act: 6.0229. Min Act: -0.1700
Data Index: 5027254 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4604. Min Range: -6.4604
Max Act: 5.9917. Min Act: -0.1700
Data Index: 2530452 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4604. Min Range: -6.4604
Max Act: 6.0229. Min Act: -0.1700
Data Index: 6995831 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4604. Min Range: -6.4604
Max Act: 5.9917. Min Act: -0.1700
Data Index: 5559126 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4604. Min Range: -6.4604
Max Act: 6.0229. Min Act: -0.1700
Data Index: 7959131 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4604. Min Range: -6.4604
Max Act: 5.9604. Min Act: -0.1700
Data Index: 525667 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #19