Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1513 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9178. Min Range: -6.9178
Max Act: 6.9178. Min Act: -0.1700
Data Index: 460164 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9178. Min Range: -6.9178
Max Act: 6.7615. Min Act: -0.1700
Data Index: 7022244 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9178. Min Range: -6.9178
Max Act: 6.7303. Min Act: -0.1700
Data Index: 6474104 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9178. Min Range: -6.9178
Max Act: 6.7303. Min Act: -0.1700
Data Index: 2681203 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9178. Min Range: -6.9178
Max Act: 6.7303. Min Act: -0.1700
Data Index: 3916143 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9178. Min Range: -6.9178
Max Act: 6.6990. Min Act: -0.1700
Data Index: 3335258 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9178. Min Range: -6.9178
Max Act: 6.6990. Min Act: -0.1700
Data Index: 6267846 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9178. Min Range: -6.9178
Max Act: 6.6365. Min Act: -0.1700
Data Index: 8293109 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9178. Min Range: -6.9178
Max Act: 6.6365. Min Act: -0.1700
Data Index: 1960042 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9178. Min Range: -6.9178
Max Act: 6.6053. Min Act: -0.1700
Data Index: 5412558 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9178. Min Range: -6.9178
Max Act: 6.5740. Min Act: -0.1700
Data Index: 5118408 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9178. Min Range: -6.9178
Max Act: 6.5428. Min Act: -0.1700
Data Index: 7007664 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9178. Min Range: -6.9178
Max Act: 6.5115. Min Act: -0.1700
Data Index: 4517698 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9178. Min Range: -6.9178
Max Act: 6.5115. Min Act: -0.1700
Data Index: 7497636 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9178. Min Range: -6.9178
Max Act: 6.5428. Min Act: -0.1700
Data Index: 7838416 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9178. Min Range: -6.9178
Max Act: 6.5428. Min Act: -0.1700
Data Index: 792734 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9178. Min Range: -6.9178
Max Act: 6.5428. Min Act: -0.1700
Data Index: 1124232 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9178. Min Range: -6.9178
Max Act: 6.5115. Min Act: -0.1700
Data Index: 2254105 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9178. Min Range: -6.9178
Max Act: 6.5740. Min Act: -0.1700
Data Index: 6865187 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9178. Min Range: -6.9178
Max Act: 6.5115. Min Act: -0.1700
Data Index: 1588879 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #19