Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3389 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7715. Min Range: -7.7715
Max Act: 7.7715. Min Act: -0.1700
Data Index: 2642803 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7715. Min Range: -7.7715
Max Act: 7.7715. Min Act: -0.1700
Data Index: 7644817 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7715. Min Range: -7.7715
Max Act: 7.7090. Min Act: -0.1700
Data Index: 34887 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7715. Min Range: -7.7715
Max Act: 7.5840. Min Act: -0.1700
Data Index: 8764949 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7715. Min Range: -7.7715
Max Act: 7.5215. Min Act: -0.1700
Data Index: 7566782 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7715. Min Range: -7.7715
Max Act: 7.5215. Min Act: -0.1700
Data Index: 6352981 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7715. Min Range: -7.7715
Max Act: 7.4278. Min Act: -0.1700
Data Index: 6000261 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7715. Min Range: -7.7715
Max Act: 7.3653. Min Act: -0.1700
Data Index: 6051222 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7715. Min Range: -7.7715
Max Act: 7.3653. Min Act: -0.1700
Data Index: 883368 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7715. Min Range: -7.7715
Max Act: 7.3340. Min Act: -0.1700
Data Index: 3020316 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7715. Min Range: -7.7715
Max Act: 7.3028. Min Act: -0.1700
Data Index: 6026232 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7715. Min Range: -7.7715
Max Act: 7.3028. Min Act: -0.1700
Data Index: 6625614 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7715. Min Range: -7.7715
Max Act: 7.3028. Min Act: -0.1700
Data Index: 4670495 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7715. Min Range: -7.7715
Max Act: 7.2403. Min Act: -0.1700
Data Index: 3687496 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7715. Min Range: -7.7715
Max Act: 7.2403. Min Act: -0.1700
Data Index: 7550816 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7715. Min Range: -7.7715
Max Act: 7.2403. Min Act: -0.1700
Data Index: 8337431 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7715. Min Range: -7.7715
Max Act: 7.2090. Min Act: -0.1700
Data Index: 5292147 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7715. Min Range: -7.7715
Max Act: 7.1778. Min Act: -0.1700
Data Index: 4469130 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7715. Min Range: -7.7715
Max Act: 7.1465. Min Act: -0.1700
Data Index: 1278473 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7715. Min Range: -7.7715
Max Act: 7.1465. Min Act: -0.1700
Data Index: 2760238 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #19