Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2982 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7726. Min Range: -4.7726
Max Act: 4.7726. Min Act: -0.1700
Data Index: 7127972 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7726. Min Range: -4.7726
Max Act: 4.7101. Min Act: -0.1700
Data Index: 88326 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7726. Min Range: -4.7726
Max Act: 4.6789. Min Act: -0.1700
Data Index: 8384289 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7726. Min Range: -4.7726
Max Act: 4.6476. Min Act: -0.1700
Data Index: 5514050 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7726. Min Range: -4.7726
Max Act: 4.6476. Min Act: -0.1700
Data Index: 8611058 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7726. Min Range: -4.7726
Max Act: 4.5851. Min Act: -0.1700
Data Index: 5481727 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7726. Min Range: -4.7726
Max Act: 4.5539. Min Act: -0.1700
Data Index: 7575321 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7726. Min Range: -4.7726
Max Act: 4.4914. Min Act: -0.1700
Data Index: 3312715 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7726. Min Range: -4.7726
Max Act: 4.4914. Min Act: -0.1700
Data Index: 2670597 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7726. Min Range: -4.7726
Max Act: 4.4289. Min Act: -0.1700
Data Index: 4808859 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7726. Min Range: -4.7726
Max Act: 4.4601. Min Act: -0.1700
Data Index: 4891051 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7726. Min Range: -4.7726
Max Act: 4.4289. Min Act: -0.1700
Data Index: 5661411 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7726. Min Range: -4.7726
Max Act: 4.4289. Min Act: -0.1700
Data Index: 5481728 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7726. Min Range: -4.7726
Max Act: 4.4289. Min Act: -0.1700
Data Index: 6590997 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7726. Min Range: -4.7726
Max Act: 4.3976. Min Act: -0.1700
Data Index: 5118627 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7726. Min Range: -4.7726
Max Act: 4.3664. Min Act: -0.1700
Data Index: 7607982 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7726. Min Range: -4.7726
Max Act: 4.3976. Min Act: -0.1700
Data Index: 5990181 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7726. Min Range: -4.7726
Max Act: 4.3976. Min Act: -0.1700
Data Index: 4643112 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7726. Min Range: -4.7726
Max Act: 4.3976. Min Act: -0.1700
Data Index: 2735845 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7726. Min Range: -4.7726
Max Act: 4.3664. Min Act: -0.1700
Data Index: 1275488 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #19