Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2993 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4275. Min Range: -7.4275
Max Act: 7.4275. Min Act: -0.1700
Data Index: 5889702 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4275. Min Range: -7.4275
Max Act: 7.0525. Min Act: -0.1700
Data Index: 2292675 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4275. Min Range: -7.4275
Max Act: 6.8025. Min Act: -0.1700
Data Index: 138177 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4275. Min Range: -7.4275
Max Act: 6.5525. Min Act: -0.1700
Data Index: 5828466 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4275. Min Range: -7.4275
Max Act: 6.5838. Min Act: -0.1700
Data Index: 4636481 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4275. Min Range: -7.4275
Max Act: 6.5838. Min Act: -0.1700
Data Index: 7169431 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4275. Min Range: -7.4275
Max Act: 6.5213. Min Act: -0.1700
Data Index: 7337202 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4275. Min Range: -7.4275
Max Act: 6.3963. Min Act: -0.1700
Data Index: 3060103 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4275. Min Range: -7.4275
Max Act: 6.4588. Min Act: -0.1700
Data Index: 2887012 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4275. Min Range: -7.4275
Max Act: 6.3963. Min Act: -0.1700
Data Index: 8639188 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4275. Min Range: -7.4275
Max Act: 6.3338. Min Act: -0.1700
Data Index: 1851882 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4275. Min Range: -7.4275
Max Act: 6.3025. Min Act: -0.1700
Data Index: 3240508 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4275. Min Range: -7.4275
Max Act: 6.3025. Min Act: -0.1700
Data Index: 5267070 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4275. Min Range: -7.4275
Max Act: 6.2400. Min Act: -0.1700
Data Index: 3504328 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4275. Min Range: -7.4275
Max Act: 6.2713. Min Act: -0.1700
Data Index: 100694 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4275. Min Range: -7.4275
Max Act: 6.2400. Min Act: -0.1700
Data Index: 2885191 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4275. Min Range: -7.4275
Max Act: 6.1775. Min Act: -0.1700
Data Index: 2761796 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4275. Min Range: -7.4275
Max Act: 6.2088. Min Act: -0.1700
Data Index: 7081261 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4275. Min Range: -7.4275
Max Act: 6.2088. Min Act: -0.1700
Data Index: 818936 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4275. Min Range: -7.4275
Max Act: 6.1775. Min Act: -0.1700
Data Index: 2453797 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #19