Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1474 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8218. Min Range: -8.8218
Max Act: 8.8218. Min Act: -0.1700
Data Index: 2816288 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8218. Min Range: -8.8218
Max Act: 8.5718. Min Act: -0.1700
Data Index: 949583 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8218. Min Range: -8.8218
Max Act: 8.4780. Min Act: -0.1700
Data Index: 7813863 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8218. Min Range: -8.8218
Max Act: 8.4468. Min Act: -0.1700
Data Index: 7067603 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8218. Min Range: -8.8218
Max Act: 8.4155. Min Act: -0.1700
Data Index: 2235904 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8218. Min Range: -8.8218
Max Act: 8.3843. Min Act: -0.1700
Data Index: 1688052 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8218. Min Range: -8.8218
Max Act: 8.2905. Min Act: -0.1700
Data Index: 1272990 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8218. Min Range: -8.8218
Max Act: 8.2905. Min Act: -0.1700
Data Index: 2426883 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8218. Min Range: -8.8218
Max Act: 8.2280. Min Act: -0.1700
Data Index: 557438 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8218. Min Range: -8.8218
Max Act: 8.2280. Min Act: -0.1700
Data Index: 237432 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8218. Min Range: -8.8218
Max Act: 8.2593. Min Act: -0.1700
Data Index: 5261009 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8218. Min Range: -8.8218
Max Act: 8.1968. Min Act: -0.1700
Data Index: 5320517 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8218. Min Range: -8.8218
Max Act: 8.1655. Min Act: -0.1700
Data Index: 2877319 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8218. Min Range: -8.8218
Max Act: 8.1343. Min Act: -0.1700
Data Index: 7168028 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8218. Min Range: -8.8218
Max Act: 8.1655. Min Act: -0.1700
Data Index: 6293298 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8218. Min Range: -8.8218
Max Act: 8.1343. Min Act: -0.1700
Data Index: 181143 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8218. Min Range: -8.8218
Max Act: 8.1343. Min Act: -0.1700
Data Index: 8690464 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8218. Min Range: -8.8218
Max Act: 8.1030. Min Act: -0.1700
Data Index: 1936309 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8218. Min Range: -8.8218
Max Act: 8.1343. Min Act: -0.1700
Data Index: 4624654 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8218. Min Range: -8.8218
Max Act: 8.1030. Min Act: -0.1700
Data Index: 3578492 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #19