Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2637 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1178. Min Range: -4.1178
Max Act: 4.1178. Min Act: -0.1700
Data Index: 4084136 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1178. Min Range: -4.1178
Max Act: 3.9927. Min Act: -0.1700
Data Index: 7250399 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1178. Min Range: -4.1178
Max Act: 3.9615. Min Act: -0.1700
Data Index: 3365740 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1178. Min Range: -4.1178
Max Act: 3.9615. Min Act: -0.1700
Data Index: 4605450 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1178. Min Range: -4.1178
Max Act: 3.9302. Min Act: -0.1700
Data Index: 3498351 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1178. Min Range: -4.1178
Max Act: 3.9302. Min Act: -0.1700
Data Index: 3089914 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1178. Min Range: -4.1178
Max Act: 3.9302. Min Act: -0.1700
Data Index: 4649022 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1178. Min Range: -4.1178
Max Act: 3.9302. Min Act: -0.1700
Data Index: 4029204 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1178. Min Range: -4.1178
Max Act: 3.9302. Min Act: -0.1700
Data Index: 3148223 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1178. Min Range: -4.1178
Max Act: 3.8989. Min Act: -0.1700
Data Index: 7715744 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1178. Min Range: -4.1178
Max Act: 3.8677. Min Act: -0.1700
Data Index: 755514 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1178. Min Range: -4.1178
Max Act: 3.8677. Min Act: -0.1700
Data Index: 6970338 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1178. Min Range: -4.1178
Max Act: 3.8677. Min Act: -0.1700
Data Index: 1470319 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1178. Min Range: -4.1178
Max Act: 3.8364. Min Act: -0.1700
Data Index: 3331701 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1178. Min Range: -4.1178
Max Act: 3.8051. Min Act: -0.1700
Data Index: 3263357 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1178. Min Range: -4.1178
Max Act: 3.7739. Min Act: -0.1700
Data Index: 2840594 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1178. Min Range: -4.1178
Max Act: 3.8051. Min Act: -0.1700
Data Index: 1940787 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1178. Min Range: -4.1178
Max Act: 3.7739. Min Act: -0.1700
Data Index: 1754001 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1178. Min Range: -4.1178
Max Act: 3.7739. Min Act: -0.1700
Data Index: 4061275 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1178. Min Range: -4.1178
Max Act: 3.7426. Min Act: -0.1700
Data Index: 2312265 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #19