Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2796 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2686. Min Range: -5.2686
Max Act: 5.2686. Min Act: -0.1700
Data Index: 88369 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2686. Min Range: -5.2686
Max Act: 5.0499. Min Act: -0.1700
Data Index: 7076587 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2686. Min Range: -5.2686
Max Act: 4.9249. Min Act: -0.1700
Data Index: 3999011 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2686. Min Range: -5.2686
Max Act: 4.9249. Min Act: -0.1700
Data Index: 6690894 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2686. Min Range: -5.2686
Max Act: 4.8624. Min Act: -0.1700
Data Index: 2680542 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2686. Min Range: -5.2686
Max Act: 4.7374. Min Act: -0.1700
Data Index: 6783775 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2686. Min Range: -5.2686
Max Act: 4.7374. Min Act: -0.1700
Data Index: 1862916 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2686. Min Range: -5.2686
Max Act: 4.7686. Min Act: -0.1700
Data Index: 7377791 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2686. Min Range: -5.2686
Max Act: 4.6749. Min Act: -0.1700
Data Index: 276041 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2686. Min Range: -5.2686
Max Act: 4.7061. Min Act: -0.1700
Data Index: 1569717 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2686. Min Range: -5.2686
Max Act: 4.7061. Min Act: -0.1700
Data Index: 3370853 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2686. Min Range: -5.2686
Max Act: 4.6749. Min Act: -0.1700
Data Index: 4502451 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2686. Min Range: -5.2686
Max Act: 4.6749. Min Act: -0.1700
Data Index: 1323 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2686. Min Range: -5.2686
Max Act: 4.6436. Min Act: -0.1700
Data Index: 7307135 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2686. Min Range: -5.2686
Max Act: 4.6436. Min Act: -0.1700
Data Index: 2279446 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2686. Min Range: -5.2686
Max Act: 4.6436. Min Act: -0.1700
Data Index: 5656528 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2686. Min Range: -5.2686
Max Act: 4.6124. Min Act: -0.1700
Data Index: 1915309 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2686. Min Range: -5.2686
Max Act: 4.6124. Min Act: -0.1700
Data Index: 3686581 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2686. Min Range: -5.2686
Max Act: 4.5811. Min Act: -0.1700
Data Index: 6078630 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2686. Min Range: -5.2686
Max Act: 4.6124. Min Act: -0.1700
Data Index: 3999010 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #19