Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2901 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1394. Min Range: -4.1394
Max Act: 4.1394. Min Act: -0.1700
Data Index: 2881042 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1394. Min Range: -4.1394
Max Act: 4.1081. Min Act: -0.1700
Data Index: 362071 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1394. Min Range: -4.1394
Max Act: 4.0456. Min Act: -0.1700
Data Index: 4099806 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1394. Min Range: -4.1394
Max Act: 4.0143. Min Act: -0.1700
Data Index: 315367 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1394. Min Range: -4.1394
Max Act: 4.0143. Min Act: -0.1700
Data Index: 7029588 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1394. Min Range: -4.1394
Max Act: 4.0143. Min Act: -0.1700
Data Index: 7011174 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1394. Min Range: -4.1394
Max Act: 3.9831. Min Act: -0.1700
Data Index: 239223 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1394. Min Range: -4.1394
Max Act: 3.9518. Min Act: -0.1700
Data Index: 6371455 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1394. Min Range: -4.1394
Max Act: 3.9205. Min Act: -0.1700
Data Index: 1937962 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1394. Min Range: -4.1394
Max Act: 3.8893. Min Act: -0.1700
Data Index: 5040903 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1394. Min Range: -4.1394
Max Act: 3.8893. Min Act: -0.1700
Data Index: 2435152 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1394. Min Range: -4.1394
Max Act: 3.8893. Min Act: -0.1700
Data Index: 7571424 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1394. Min Range: -4.1394
Max Act: 3.8580. Min Act: -0.1700
Data Index: 3555884 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1394. Min Range: -4.1394
Max Act: 3.8580. Min Act: -0.1700
Data Index: 2319530 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1394. Min Range: -4.1394
Max Act: 3.8580. Min Act: -0.1700
Data Index: 1557598 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1394. Min Range: -4.1394
Max Act: 3.8580. Min Act: -0.1700
Data Index: 362078 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1394. Min Range: -4.1394
Max Act: 3.8580. Min Act: -0.1700
Data Index: 3485564 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1394. Min Range: -4.1394
Max Act: 3.8267. Min Act: -0.1700
Data Index: 362072 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1394. Min Range: -4.1394
Max Act: 3.8267. Min Act: -0.1700
Data Index: 3029009 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1394. Min Range: -4.1394
Max Act: 3.8267. Min Act: -0.1700
Data Index: 4947640 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #19