Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1001 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0589. Min Range: -3.0589
Max Act: 3.0589. Min Act: -0.1700
Data Index: 1487995 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0589. Min Range: -3.0589
Max Act: 2.8531. Min Act: -0.1700
Data Index: 4842774 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0589. Min Range: -3.0589
Max Act: 2.8531. Min Act: -0.1700
Data Index: 5592674 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0589. Min Range: -3.0589
Max Act: 2.8372. Min Act: -0.1700
Data Index: 3869870 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0589. Min Range: -3.0589
Max Act: 2.8213. Min Act: -0.1700
Data Index: 6367627 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0589. Min Range: -3.0589
Max Act: 2.8372. Min Act: -0.1700
Data Index: 7939419 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0589. Min Range: -3.0589
Max Act: 2.8054. Min Act: -0.1700
Data Index: 7177926 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0589. Min Range: -3.0589
Max Act: 2.8054. Min Act: -0.1700
Data Index: 4605601 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0589. Min Range: -3.0589
Max Act: 2.8054. Min Act: -0.1700
Data Index: 4779915 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0589. Min Range: -3.0589
Max Act: 2.7894. Min Act: -0.1700
Data Index: 1026908 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0589. Min Range: -3.0589
Max Act: 2.7576. Min Act: -0.1700
Data Index: 2539844 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0589. Min Range: -3.0589
Max Act: 2.7735. Min Act: -0.1700
Data Index: 175676 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0589. Min Range: -3.0589
Max Act: 2.7576. Min Act: -0.1700
Data Index: 4601876 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0589. Min Range: -3.0589
Max Act: 2.7576. Min Act: -0.1700
Data Index: 2080857 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0589. Min Range: -3.0589
Max Act: 2.7576. Min Act: -0.1700
Data Index: 7030668 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0589. Min Range: -3.0589
Max Act: 2.7576. Min Act: -0.1700
Data Index: 3521918 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0589. Min Range: -3.0589
Max Act: 2.7735. Min Act: -0.1700
Data Index: 2074161 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0589. Min Range: -3.0589
Max Act: 2.7416. Min Act: -0.1700
Data Index: 5664342 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0589. Min Range: -3.0589
Max Act: 2.7256. Min Act: -0.1700
Data Index: 5564214 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0589. Min Range: -3.0589
Max Act: 2.7416. Min Act: -0.1700
Data Index: 820372 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #19