Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3681 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6338. Min Range: -6.6338
Max Act: 6.6338. Min Act: -0.1700
Data Index: 6518655 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6338. Min Range: -6.6338
Max Act: 6.6338. Min Act: -0.1700
Data Index: 1723621 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6338. Min Range: -6.6338
Max Act: 6.5713. Min Act: -0.1700
Data Index: 8583641 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6338. Min Range: -6.6338
Max Act: 6.5401. Min Act: -0.1700
Data Index: 6142461 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6338. Min Range: -6.6338
Max Act: 6.4776. Min Act: -0.1700
Data Index: 7794426 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6338. Min Range: -6.6338
Max Act: 6.4463. Min Act: -0.1700
Data Index: 6194630 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6338. Min Range: -6.6338
Max Act: 6.3526. Min Act: -0.1700
Data Index: 6115724 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6338. Min Range: -6.6338
Max Act: 6.3838. Min Act: -0.1700
Data Index: 3501728 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6338. Min Range: -6.6338
Max Act: 6.3838. Min Act: -0.1700
Data Index: 67621 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6338. Min Range: -6.6338
Max Act: 6.3526. Min Act: -0.1700
Data Index: 3857888 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6338. Min Range: -6.6338
Max Act: 6.3526. Min Act: -0.1700
Data Index: 7409579 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6338. Min Range: -6.6338
Max Act: 6.3213. Min Act: -0.1700
Data Index: 7019062 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6338. Min Range: -6.6338
Max Act: 6.2901. Min Act: -0.1700
Data Index: 192267 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6338. Min Range: -6.6338
Max Act: 6.2901. Min Act: -0.1700
Data Index: 301683 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6338. Min Range: -6.6338
Max Act: 6.2901. Min Act: -0.1700
Data Index: 6495953 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6338. Min Range: -6.6338
Max Act: 6.2901. Min Act: -0.1700
Data Index: 3920001 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6338. Min Range: -6.6338
Max Act: 6.2901. Min Act: -0.1700
Data Index: 6968211 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6338. Min Range: -6.6338
Max Act: 6.2588. Min Act: -0.1700
Data Index: 6183666 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6338. Min Range: -6.6338
Max Act: 6.2588. Min Act: -0.1700
Data Index: 5640987 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6338. Min Range: -6.6338
Max Act: 6.2276. Min Act: -0.1700
Data Index: 1543867 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #19