Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1409 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5267. Min Range: -4.5267
Max Act: 4.5267. Min Act: -0.1700
Data Index: 1052218 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5267. Min Range: -4.5267
Max Act: 4.3392. Min Act: -0.1700
Data Index: 3526985 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5267. Min Range: -4.5267
Max Act: 4.3080. Min Act: -0.1700
Data Index: 6234964 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5267. Min Range: -4.5267
Max Act: 4.3080. Min Act: -0.1700
Data Index: 1122689 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5267. Min Range: -4.5267
Max Act: 4.2767. Min Act: -0.1700
Data Index: 2154724 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5267. Min Range: -4.5267
Max Act: 4.2767. Min Act: -0.1700
Data Index: 3072284 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5267. Min Range: -4.5267
Max Act: 4.1830. Min Act: -0.1700
Data Index: 2289923 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5267. Min Range: -4.5267
Max Act: 4.1517. Min Act: -0.1700
Data Index: 4326653 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5267. Min Range: -4.5267
Max Act: 4.1517. Min Act: -0.1700
Data Index: 638866 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5267. Min Range: -4.5267
Max Act: 4.1517. Min Act: -0.1700
Data Index: 4681723 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5267. Min Range: -4.5267
Max Act: 4.1517. Min Act: -0.1700
Data Index: 8461741 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5267. Min Range: -4.5267
Max Act: 4.1204. Min Act: -0.1700
Data Index: 8105397 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5267. Min Range: -4.5267
Max Act: 4.1204. Min Act: -0.1700
Data Index: 2933465 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5267. Min Range: -4.5267
Max Act: 4.0892. Min Act: -0.1700
Data Index: 3038838 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5267. Min Range: -4.5267
Max Act: 4.1204. Min Act: -0.1700
Data Index: 3841920 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5267. Min Range: -4.5267
Max Act: 4.0892. Min Act: -0.1700
Data Index: 6253549 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5267. Min Range: -4.5267
Max Act: 4.0579. Min Act: -0.1700
Data Index: 6223299 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5267. Min Range: -4.5267
Max Act: 4.0579. Min Act: -0.1700
Data Index: 5763807 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5267. Min Range: -4.5267
Max Act: 4.0579. Min Act: -0.1700
Data Index: 3041929 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5267. Min Range: -4.5267
Max Act: 4.0579. Min Act: -0.1700
Data Index: 165462 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #19