Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4448 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9729. Min Range: -6.9729
Max Act: 6.9729. Min Act: -0.1700
Data Index: 6599525 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9729. Min Range: -6.9729
Max Act: 6.7854. Min Act: -0.1700
Data Index: 7097918 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9729. Min Range: -6.9729
Max Act: 6.7229. Min Act: -0.1700
Data Index: 6359413 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9729. Min Range: -6.9729
Max Act: 6.5979. Min Act: -0.1700
Data Index: 822564 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9729. Min Range: -6.9729
Max Act: 6.4417. Min Act: -0.1700
Data Index: 903635 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9729. Min Range: -6.9729
Max Act: 6.4104. Min Act: -0.1700
Data Index: 6177943 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9729. Min Range: -6.9729
Max Act: 6.3479. Min Act: -0.1700
Data Index: 4212880 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9729. Min Range: -6.9729
Max Act: 6.3479. Min Act: -0.1700
Data Index: 7814181 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9729. Min Range: -6.9729
Max Act: 6.3167. Min Act: -0.1700
Data Index: 7659113 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9729. Min Range: -6.9729
Max Act: 6.3167. Min Act: -0.1700
Data Index: 920011 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9729. Min Range: -6.9729
Max Act: 6.2854. Min Act: -0.1700
Data Index: 628999 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9729. Min Range: -6.9729
Max Act: 6.2542. Min Act: -0.1700
Data Index: 739119 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9729. Min Range: -6.9729
Max Act: 6.2542. Min Act: -0.1700
Data Index: 4976297 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9729. Min Range: -6.9729
Max Act: 6.2229. Min Act: -0.1700
Data Index: 1510951 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9729. Min Range: -6.9729
Max Act: 6.2229. Min Act: -0.1700
Data Index: 4212882 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9729. Min Range: -6.9729
Max Act: 6.1917. Min Act: -0.1700
Data Index: 4992330 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9729. Min Range: -6.9729
Max Act: 6.1917. Min Act: -0.1700
Data Index: 2427854 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9729. Min Range: -6.9729
Max Act: 6.1917. Min Act: -0.1700
Data Index: 5927297 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9729. Min Range: -6.9729
Max Act: 6.1917. Min Act: -0.1700
Data Index: 6857087 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9729. Min Range: -6.9729
Max Act: 6.1917. Min Act: -0.1700
Data Index: 5579539 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #19