Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2870 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3820. Min Range: -4.3820
Max Act: 4.3820. Min Act: -0.1700
Data Index: 776257 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3820. Min Range: -4.3820
Max Act: 4.2570. Min Act: -0.1700
Data Index: 904160 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3820. Min Range: -4.3820
Max Act: 4.1945. Min Act: -0.1700
Data Index: 6269647 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3820. Min Range: -4.3820
Max Act: 4.1945. Min Act: -0.1700
Data Index: 8555884 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3820. Min Range: -4.3820
Max Act: 4.1945. Min Act: -0.1699
Data Index: 3250515 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3820. Min Range: -4.3820
Max Act: 4.1633. Min Act: -0.1700
Data Index: 7641247 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3820. Min Range: -4.3820
Max Act: 4.1320. Min Act: -0.1700
Data Index: 5750398 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3820. Min Range: -4.3820
Max Act: 4.0695. Min Act: -0.1700
Data Index: 2318995 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3820. Min Range: -4.3820
Max Act: 4.0695. Min Act: -0.1699
Data Index: 3250521 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3820. Min Range: -4.3820
Max Act: 4.0382. Min Act: -0.1700
Data Index: 6248365 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3820. Min Range: -4.3820
Max Act: 4.0382. Min Act: -0.1700
Data Index: 8226338 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3820. Min Range: -4.3820
Max Act: 4.0070. Min Act: -0.1700
Data Index: 8507352 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3820. Min Range: -4.3820
Max Act: 4.0382. Min Act: -0.1700
Data Index: 8190694 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3820. Min Range: -4.3820
Max Act: 4.0070. Min Act: -0.1700
Data Index: 2421850 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3820. Min Range: -4.3820
Max Act: 3.9757. Min Act: -0.1700
Data Index: 5432974 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3820. Min Range: -4.3820
Max Act: 3.9757. Min Act: -0.1700
Data Index: 816572 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3820. Min Range: -4.3820
Max Act: 3.9757. Min Act: -0.1700
Data Index: 4440032 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3820. Min Range: -4.3820
Max Act: 3.9757. Min Act: -0.1700
Data Index: 2793531 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3820. Min Range: -4.3820
Max Act: 3.9757. Min Act: -0.1700
Data Index: 124649 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3820. Min Range: -4.3820
Max Act: 3.9757. Min Act: -0.1700
Data Index: 6217449 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #19