Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 683 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.3562. Min Range: -2.3562
Max Act: 2.3562. Min Act: -0.1700
Data Index: 2926120 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3562. Min Range: -2.3562
Max Act: 2.3562. Min Act: -0.1700
Data Index: 7892906 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3562. Min Range: -2.3562
Max Act: 2.3398. Min Act: -0.1700
Data Index: 4103948 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3562. Min Range: -2.3562
Max Act: 2.3234. Min Act: -0.1700
Data Index: 3191613 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3562. Min Range: -2.3562
Max Act: 2.3070. Min Act: -0.1700
Data Index: 5455040 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3562. Min Range: -2.3562
Max Act: 2.3234. Min Act: -0.1700
Data Index: 7978385 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3562. Min Range: -2.3562
Max Act: 2.3234. Min Act: -0.1700
Data Index: 7315036 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3562. Min Range: -2.3562
Max Act: 2.3070. Min Act: -0.1700
Data Index: 924164 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3562. Min Range: -2.3562
Max Act: 2.3070. Min Act: -0.1700
Data Index: 4848873 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3562. Min Range: -2.3562
Max Act: 2.2905. Min Act: -0.1700
Data Index: 5786934 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3562. Min Range: -2.3562
Max Act: 2.3070. Min Act: -0.1700
Data Index: 5305383 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3562. Min Range: -2.3562
Max Act: 2.2905. Min Act: -0.1700
Data Index: 1186578 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3562. Min Range: -2.3562
Max Act: 2.2905. Min Act: -0.1700
Data Index: 2502654 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3562. Min Range: -2.3562
Max Act: 2.2576. Min Act: -0.1700
Data Index: 6793890 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3562. Min Range: -2.3562
Max Act: 2.2741. Min Act: -0.1700
Data Index: 2634674 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3562. Min Range: -2.3562
Max Act: 2.2410. Min Act: -0.1700
Data Index: 1800230 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3562. Min Range: -2.3562
Max Act: 2.2576. Min Act: -0.1700
Data Index: 5852493 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3562. Min Range: -2.3562
Max Act: 2.2410. Min Act: -0.1700
Data Index: 7382442 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3562. Min Range: -2.3562
Max Act: 2.2576. Min Act: -0.1700
Data Index: 6390829 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3562. Min Range: -2.3562
Max Act: 2.2410. Min Act: -0.1700
Data Index: 4139365 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #19