Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2142 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7376. Min Range: -5.7376
Max Act: 5.7376. Min Act: -0.1700
Data Index: 7631944 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7376. Min Range: -5.7376
Max Act: 5.6751. Min Act: -0.1700
Data Index: 6522642 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7376. Min Range: -5.7376
Max Act: 5.6126. Min Act: -0.1700
Data Index: 7122060 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7376. Min Range: -5.7376
Max Act: 5.5501. Min Act: -0.1700
Data Index: 2449801 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7376. Min Range: -5.7376
Max Act: 5.5501. Min Act: -0.1700
Data Index: 4004205 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7376. Min Range: -5.7376
Max Act: 5.5189. Min Act: -0.1700
Data Index: 5223825 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7376. Min Range: -5.7376
Max Act: 5.4564. Min Act: -0.1700
Data Index: 1085805 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7376. Min Range: -5.7376
Max Act: 5.4564. Min Act: -0.1700
Data Index: 7056093 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7376. Min Range: -5.7376
Max Act: 5.4251. Min Act: -0.1700
Data Index: 4318498 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7376. Min Range: -5.7376
Max Act: 5.4251. Min Act: -0.1700
Data Index: 5318878 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7376. Min Range: -5.7376
Max Act: 5.3939. Min Act: -0.1700
Data Index: 394517 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7376. Min Range: -5.7376
Max Act: 5.3626. Min Act: -0.1700
Data Index: 4253253 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7376. Min Range: -5.7376
Max Act: 5.3626. Min Act: -0.1700
Data Index: 8069753 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7376. Min Range: -5.7376
Max Act: 5.3626. Min Act: -0.1700
Data Index: 3175462 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7376. Min Range: -5.7376
Max Act: 5.3001. Min Act: -0.1700
Data Index: 5360659 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7376. Min Range: -5.7376
Max Act: 5.3001. Min Act: -0.1700
Data Index: 6561951 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7376. Min Range: -5.7376
Max Act: 5.3001. Min Act: -0.1700
Data Index: 3130569 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7376. Min Range: -5.7376
Max Act: 5.2689. Min Act: -0.1700
Data Index: 7760211 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7376. Min Range: -5.7376
Max Act: 5.2689. Min Act: -0.1700
Data Index: 6814322 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7376. Min Range: -5.7376
Max Act: 5.2376. Min Act: -0.1700
Data Index: 7333730 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #19