Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2872 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.2723. Min Range: -11.2723
Max Act: 11.2723. Min Act: -0.1700
Data Index: 5794476 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.2723. Min Range: -11.2723
Max Act: 11.2098. Min Act: -0.1700
Data Index: 1613334 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.2723. Min Range: -11.2723
Max Act: 11.2098. Min Act: -0.1700
Data Index: 2445232 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.2723. Min Range: -11.2723
Max Act: 11.2723. Min Act: -0.1700
Data Index: 3652959 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.2723. Min Range: -11.2723
Max Act: 10.8973. Min Act: -0.1700
Data Index: 4453128 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.2723. Min Range: -11.2723
Max Act: 10.8348. Min Act: -0.1700
Data Index: 3208891 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.2723. Min Range: -11.2723
Max Act: 10.8348. Min Act: -0.1700
Data Index: 3768782 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.2723. Min Range: -11.2723
Max Act: 10.8348. Min Act: -0.1700
Data Index: 3680921 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.2723. Min Range: -11.2723
Max Act: 10.8973. Min Act: -0.1700
Data Index: 2108279 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.2723. Min Range: -11.2723
Max Act: 10.8348. Min Act: -0.1700
Data Index: 5056074 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.2723. Min Range: -11.2723
Max Act: 10.7723. Min Act: -0.1700
Data Index: 4221959 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.2723. Min Range: -11.2723
Max Act: 10.7723. Min Act: -0.1700
Data Index: 6203005 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.2723. Min Range: -11.2723
Max Act: 10.7723. Min Act: -0.1700
Data Index: 4414955 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.2723. Min Range: -11.2723
Max Act: 10.7723. Min Act: -0.1700
Data Index: 5652550 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.2723. Min Range: -11.2723
Max Act: 10.7723. Min Act: -0.1700
Data Index: 7011280 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.2723. Min Range: -11.2723
Max Act: 10.7098. Min Act: -0.1700
Data Index: 1724523 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.2723. Min Range: -11.2723
Max Act: 10.7098. Min Act: -0.1700
Data Index: 8036437 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.2723. Min Range: -11.2723
Max Act: 10.7098. Min Act: -0.1700
Data Index: 732204 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.2723. Min Range: -11.2723
Max Act: 10.7098. Min Act: -0.1700
Data Index: 7450455 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.2723. Min Range: -11.2723
Max Act: 10.7098. Min Act: -0.1700
Data Index: 6005364 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #19