Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3581 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.2987. Min Range: -12.2987
Max Act: 12.2987. Min Act: -0.1700
Data Index: 7858073 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.2987. Min Range: -12.2987
Max Act: 11.9862. Min Act: -0.1700
Data Index: 3317617 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.2987. Min Range: -12.2987
Max Act: 12.0487. Min Act: -0.1700
Data Index: 4863451 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.2987. Min Range: -12.2987
Max Act: 11.7362. Min Act: -0.1700
Data Index: 6584007 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.2987. Min Range: -12.2987
Max Act: 11.7987. Min Act: -0.1700
Data Index: 5686659 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.2987. Min Range: -12.2987
Max Act: 11.6737. Min Act: -0.1700
Data Index: 3333000 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.2987. Min Range: -12.2987
Max Act: 11.6112. Min Act: -0.1700
Data Index: 6551241 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.2987. Min Range: -12.2987
Max Act: 11.5487. Min Act: -0.1700
Data Index: 497126 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.2987. Min Range: -12.2987
Max Act: 11.4862. Min Act: -0.1700
Data Index: 1971969 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.2987. Min Range: -12.2987
Max Act: 11.4862. Min Act: -0.1700
Data Index: 1510499 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.2987. Min Range: -12.2987
Max Act: 11.4862. Min Act: -0.1700
Data Index: 1900424 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.2987. Min Range: -12.2987
Max Act: 11.4237. Min Act: -0.1700
Data Index: 8406251 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.2987. Min Range: -12.2987
Max Act: 11.4237. Min Act: -0.1700
Data Index: 6972980 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.2987. Min Range: -12.2987
Max Act: 11.4237. Min Act: -0.1700
Data Index: 889219 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.2987. Min Range: -12.2987
Max Act: 11.3612. Min Act: -0.1700
Data Index: 614321 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.2987. Min Range: -12.2987
Max Act: 11.3612. Min Act: -0.1700
Data Index: 1010225 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.2987. Min Range: -12.2987
Max Act: 11.2987. Min Act: -0.1700
Data Index: 7894558 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.2987. Min Range: -12.2987
Max Act: 11.2987. Min Act: -0.1700
Data Index: 4671795 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.2987. Min Range: -12.2987
Max Act: 11.2987. Min Act: -0.1700
Data Index: 4408645 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.2987. Min Range: -12.2987
Max Act: 11.3612. Min Act: -0.1700
Data Index: 3405880 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #19