Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3467 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4549. Min Range: -6.4549
Max Act: 6.4549. Min Act: -0.1700
Data Index: 6433143 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4549. Min Range: -6.4549
Max Act: 6.3611. Min Act: -0.1700
Data Index: 3169667 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4549. Min Range: -6.4549
Max Act: 6.1424. Min Act: -0.1700
Data Index: 3803624 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4549. Min Range: -6.4549
Max Act: 6.1424. Min Act: -0.1700
Data Index: 2320455 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4549. Min Range: -6.4549
Max Act: 5.9861. Min Act: -0.1700
Data Index: 6413015 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4549. Min Range: -6.4549
Max Act: 5.8924. Min Act: -0.1700
Data Index: 2022408 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4549. Min Range: -6.4549
Max Act: 5.6424. Min Act: -0.1700
Data Index: 2087180 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4549. Min Range: -6.4549
Max Act: 5.6111. Min Act: -0.1700
Data Index: 744344 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4549. Min Range: -6.4549
Max Act: 5.6111. Min Act: -0.1700
Data Index: 8498608 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4549. Min Range: -6.4549
Max Act: 5.5799. Min Act: -0.1700
Data Index: 4055010 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4549. Min Range: -6.4549
Max Act: 5.5799. Min Act: -0.1700
Data Index: 4545960 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4549. Min Range: -6.4549
Max Act: 5.5799. Min Act: -0.1700
Data Index: 4506481 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4549. Min Range: -6.4549
Max Act: 5.5799. Min Act: -0.1700
Data Index: 3748120 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4549. Min Range: -6.4549
Max Act: 5.5486. Min Act: -0.1700
Data Index: 3835107 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4549. Min Range: -6.4549
Max Act: 5.5486. Min Act: -0.1700
Data Index: 7040511 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4549. Min Range: -6.4549
Max Act: 5.5486. Min Act: -0.1700
Data Index: 8353692 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4549. Min Range: -6.4549
Max Act: 5.5174. Min Act: -0.1700
Data Index: 8498604 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4549. Min Range: -6.4549
Max Act: 5.5174. Min Act: -0.1700
Data Index: 4246339 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4549. Min Range: -6.4549
Max Act: 5.4549. Min Act: -0.1700
Data Index: 8353703 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4549. Min Range: -6.4549
Max Act: 5.4549. Min Act: -0.1700
Data Index: 8481529 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #19