Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6079 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3178. Min Range: -6.3178
Max Act: 6.3178. Min Act: -0.1700
Data Index: 504364 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3178. Min Range: -6.3178
Max Act: 5.4116. Min Act: -0.1700
Data Index: 5596551 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3178. Min Range: -6.3178
Max Act: 5.3491. Min Act: -0.1700
Data Index: 6102664 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3178. Min Range: -6.3178
Max Act: 5.3178. Min Act: -0.1700
Data Index: 6001240 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3178. Min Range: -6.3178
Max Act: 5.3178. Min Act: -0.1700
Data Index: 7125489 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3178. Min Range: -6.3178
Max Act: 5.2553. Min Act: -0.1700
Data Index: 2519386 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3178. Min Range: -6.3178
Max Act: 5.2553. Min Act: -0.1700
Data Index: 2266821 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3178. Min Range: -6.3178
Max Act: 5.2241. Min Act: -0.1700
Data Index: 4471229 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3178. Min Range: -6.3178
Max Act: 5.2241. Min Act: -0.1700
Data Index: 3579305 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3178. Min Range: -6.3178
Max Act: 5.1616. Min Act: -0.1700
Data Index: 3974371 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3178. Min Range: -6.3178
Max Act: 5.1616. Min Act: -0.1700
Data Index: 7871684 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3178. Min Range: -6.3178
Max Act: 5.1616. Min Act: -0.1700
Data Index: 6897606 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3178. Min Range: -6.3178
Max Act: 5.1303. Min Act: -0.1700
Data Index: 7623915 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3178. Min Range: -6.3178
Max Act: 5.1303. Min Act: -0.1700
Data Index: 8666572 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3178. Min Range: -6.3178
Max Act: 5.1303. Min Act: -0.1700
Data Index: 5352528 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3178. Min Range: -6.3178
Max Act: 5.0991. Min Act: -0.1700
Data Index: 4735768 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3178. Min Range: -6.3178
Max Act: 5.0991. Min Act: -0.1700
Data Index: 1505488 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3178. Min Range: -6.3178
Max Act: 5.0678. Min Act: -0.1700
Data Index: 5912630 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3178. Min Range: -6.3178
Max Act: 5.0678. Min Act: -0.1700
Data Index: 3675885 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3178. Min Range: -6.3178
Max Act: 5.0678. Min Act: -0.1700
Data Index: 4457243 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #19