Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3026 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4975. Min Range: -6.4975
Max Act: 6.4662. Min Act: -0.1700
Data Index: 2544738 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4975. Min Range: -6.4975
Max Act: 6.4662. Min Act: -0.1700
Data Index: 6976396 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4975. Min Range: -6.4975
Max Act: 6.4662. Min Act: -0.1700
Data Index: 104392 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4975. Min Range: -6.4975
Max Act: 6.4975. Min Act: -0.1700
Data Index: 5782201 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4975. Min Range: -6.4975
Max Act: 6.2475. Min Act: -0.1700
Data Index: 3818099 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4975. Min Range: -6.4975
Max Act: 6.2475. Min Act: -0.1700
Data Index: 7511632 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4975. Min Range: -6.4975
Max Act: 6.2162. Min Act: -0.1700
Data Index: 7513501 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4975. Min Range: -6.4975
Max Act: 6.2162. Min Act: -0.1700
Data Index: 827091 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4975. Min Range: -6.4975
Max Act: 6.1537. Min Act: -0.1700
Data Index: 4074475 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4975. Min Range: -6.4975
Max Act: 6.1537. Min Act: -0.1700
Data Index: 64023 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4975. Min Range: -6.4975
Max Act: 6.1537. Min Act: -0.1700
Data Index: 5666105 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4975. Min Range: -6.4975
Max Act: 6.1537. Min Act: -0.1700
Data Index: 1708722 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4975. Min Range: -6.4975
Max Act: 6.1225. Min Act: -0.1700
Data Index: 8253715 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4975. Min Range: -6.4975
Max Act: 6.1225. Min Act: -0.1700
Data Index: 3377351 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4975. Min Range: -6.4975
Max Act: 6.0912. Min Act: -0.1700
Data Index: 6381482 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4975. Min Range: -6.4975
Max Act: 6.1225. Min Act: -0.1700
Data Index: 2656730 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4975. Min Range: -6.4975
Max Act: 6.0912. Min Act: -0.1700
Data Index: 5695716 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4975. Min Range: -6.4975
Max Act: 6.0912. Min Act: -0.1700
Data Index: 3423628 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4975. Min Range: -6.4975
Max Act: 6.0912. Min Act: -0.1700
Data Index: 5789244 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4975. Min Range: -6.4975
Max Act: 6.0912. Min Act: -0.1700
Data Index: 1922341 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #19