Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2921 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1788. Min Range: -7.1788
Max Act: 7.1788. Min Act: -0.1700
Data Index: 8244351 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1788. Min Range: -7.1788
Max Act: 7.1788. Min Act: -0.1700
Data Index: 591204 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1788. Min Range: -7.1788
Max Act: 7.0226. Min Act: -0.1700
Data Index: 6604826 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1788. Min Range: -7.1788
Max Act: 7.0538. Min Act: -0.1700
Data Index: 2926937 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1788. Min Range: -7.1788
Max Act: 6.9913. Min Act: -0.1700
Data Index: 1106168 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1788. Min Range: -7.1788
Max Act: 6.9288. Min Act: -0.1700
Data Index: 4574587 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1788. Min Range: -7.1788
Max Act: 6.9288. Min Act: -0.1700
Data Index: 1251716 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1788. Min Range: -7.1788
Max Act: 6.8976. Min Act: -0.1700
Data Index: 6660137 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1788. Min Range: -7.1788
Max Act: 6.8663. Min Act: -0.1700
Data Index: 5512946 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1788. Min Range: -7.1788
Max Act: 6.8663. Min Act: -0.1700
Data Index: 4507557 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1788. Min Range: -7.1788
Max Act: 6.8038. Min Act: -0.1700
Data Index: 8442836 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1788. Min Range: -7.1788
Max Act: 6.8038. Min Act: -0.1700
Data Index: 7186633 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1788. Min Range: -7.1788
Max Act: 6.8038. Min Act: -0.1700
Data Index: 3713936 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1788. Min Range: -7.1788
Max Act: 6.7726. Min Act: -0.1700
Data Index: 4517237 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1788. Min Range: -7.1788
Max Act: 6.7726. Min Act: -0.1700
Data Index: 2002548 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1788. Min Range: -7.1788
Max Act: 6.6788. Min Act: -0.1700
Data Index: 1014925 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1788. Min Range: -7.1788
Max Act: 6.6476. Min Act: -0.1700
Data Index: 4031533 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1788. Min Range: -7.1788
Max Act: 6.7101. Min Act: -0.1700
Data Index: 6601977 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1788. Min Range: -7.1788
Max Act: 6.6163. Min Act: -0.1700
Data Index: 3924666 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1788. Min Range: -7.1788
Max Act: 6.6476. Min Act: -0.1700
Data Index: 7410594 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #19