Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5019 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6696. Min Range: -4.6696
Max Act: 4.6696. Min Act: -0.1700
Data Index: 2209893 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6696. Min Range: -4.6696
Max Act: 4.5134. Min Act: -0.1700
Data Index: 7526329 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6696. Min Range: -4.6696
Max Act: 4.4821. Min Act: -0.1700
Data Index: 4147803 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6696. Min Range: -4.6696
Max Act: 4.5134. Min Act: -0.1700
Data Index: 720693 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6696. Min Range: -4.6696
Max Act: 4.3884. Min Act: -0.1700
Data Index: 7011382 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6696. Min Range: -4.6696
Max Act: 4.3884. Min Act: -0.1700
Data Index: 6651822 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6696. Min Range: -4.6696
Max Act: 4.3571. Min Act: -0.1700
Data Index: 8567398 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6696. Min Range: -4.6696
Max Act: 4.3571. Min Act: -0.1700
Data Index: 8453512 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6696. Min Range: -4.6696
Max Act: 4.3571. Min Act: -0.1700
Data Index: 6541284 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6696. Min Range: -4.6696
Max Act: 4.3571. Min Act: -0.1700
Data Index: 8488369 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6696. Min Range: -4.6696
Max Act: 4.3571. Min Act: -0.1700
Data Index: 4711448 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6696. Min Range: -4.6696
Max Act: 4.2634. Min Act: -0.1700
Data Index: 2971885 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6696. Min Range: -4.6696
Max Act: 4.2946. Min Act: -0.1700
Data Index: 837484 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6696. Min Range: -4.6696
Max Act: 4.2946. Min Act: -0.1700
Data Index: 397357 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6696. Min Range: -4.6696
Max Act: 4.2634. Min Act: -0.1700
Data Index: 1456099 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6696. Min Range: -4.6696
Max Act: 4.2634. Min Act: -0.1700
Data Index: 1393970 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6696. Min Range: -4.6696
Max Act: 4.2946. Min Act: -0.1700
Data Index: 1366814 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6696. Min Range: -4.6696
Max Act: 4.2321. Min Act: -0.1700
Data Index: 1632191 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6696. Min Range: -4.6696
Max Act: 4.2634. Min Act: -0.1700
Data Index: 3781715 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6696. Min Range: -4.6696
Max Act: 4.2321. Min Act: -0.1700
Data Index: 7023476 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #19