Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4833 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8338. Min Range: -8.8338
Max Act: 8.8338. Min Act: -0.1700
Data Index: 1800927 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8338. Min Range: -8.8338
Max Act: 8.7088. Min Act: -0.1700
Data Index: 8193344 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8338. Min Range: -8.8338
Max Act: 8.6463. Min Act: -0.1700
Data Index: 3602850 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8338. Min Range: -8.8338
Max Act: 8.6463. Min Act: -0.1700
Data Index: 2813942 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8338. Min Range: -8.8338
Max Act: 8.5213. Min Act: -0.1700
Data Index: 4659541 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8338. Min Range: -8.8338
Max Act: 8.4588. Min Act: -0.1700
Data Index: 4390051 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8338. Min Range: -8.8338
Max Act: 8.4588. Min Act: -0.1700
Data Index: 2523494 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8338. Min Range: -8.8338
Max Act: 8.3963. Min Act: -0.1700
Data Index: 1424923 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8338. Min Range: -8.8338
Max Act: 8.3338. Min Act: -0.1700
Data Index: 5664128 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8338. Min Range: -8.8338
Max Act: 8.3338. Min Act: -0.1700
Data Index: 3627700 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8338. Min Range: -8.8338
Max Act: 8.3026. Min Act: -0.1700
Data Index: 3593394 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8338. Min Range: -8.8338
Max Act: 8.3026. Min Act: -0.1700
Data Index: 5194280 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8338. Min Range: -8.8338
Max Act: 8.3026. Min Act: -0.1700
Data Index: 3214665 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8338. Min Range: -8.8338
Max Act: 8.2713. Min Act: -0.1700
Data Index: 628880 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8338. Min Range: -8.8338
Max Act: 8.2713. Min Act: -0.1700
Data Index: 1043946 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8338. Min Range: -8.8338
Max Act: 8.2401. Min Act: -0.1700
Data Index: 5681695 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8338. Min Range: -8.8338
Max Act: 8.2088. Min Act: -0.1700
Data Index: 8577550 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8338. Min Range: -8.8338
Max Act: 8.2401. Min Act: -0.1700
Data Index: 5515594 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8338. Min Range: -8.8338
Max Act: 8.1151. Min Act: -0.1700
Data Index: 295254 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8338. Min Range: -8.8338
Max Act: 8.1151. Min Act: -0.1700
Data Index: 340574 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #19