Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4040 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5703. Min Range: -4.5703
Max Act: 4.5703. Min Act: -0.1700
Data Index: 7923562 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5703. Min Range: -4.5703
Max Act: 4.5703. Min Act: -0.1700
Data Index: 1526658 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5703. Min Range: -4.5703
Max Act: 4.5391. Min Act: -0.1700
Data Index: 7384219 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5703. Min Range: -4.5703
Max Act: 4.5078. Min Act: -0.1700
Data Index: 1795175 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5703. Min Range: -4.5703
Max Act: 4.5391. Min Act: -0.1700
Data Index: 5360701 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5703. Min Range: -4.5703
Max Act: 4.4766. Min Act: -0.1700
Data Index: 4554019 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5703. Min Range: -4.5703
Max Act: 4.4453. Min Act: -0.1700
Data Index: 2584045 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5703. Min Range: -4.5703
Max Act: 4.4453. Min Act: -0.1700
Data Index: 1851808 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5703. Min Range: -4.5703
Max Act: 4.4453. Min Act: -0.1700
Data Index: 3664318 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5703. Min Range: -4.5703
Max Act: 4.4141. Min Act: -0.1700
Data Index: 4992775 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5703. Min Range: -4.5703
Max Act: 4.4453. Min Act: -0.1700
Data Index: 4313686 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5703. Min Range: -4.5703
Max Act: 4.4141. Min Act: -0.1700
Data Index: 1709397 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5703. Min Range: -4.5703
Max Act: 4.4141. Min Act: -0.1700
Data Index: 6451209 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5703. Min Range: -4.5703
Max Act: 4.4141. Min Act: -0.1700
Data Index: 8708231 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5703. Min Range: -4.5703
Max Act: 4.4141. Min Act: -0.1700
Data Index: 264687 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5703. Min Range: -4.5703
Max Act: 4.3516. Min Act: -0.1700
Data Index: 3377891 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5703. Min Range: -4.5703
Max Act: 4.3203. Min Act: -0.1700
Data Index: 264688 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5703. Min Range: -4.5703
Max Act: 4.3203. Min Act: -0.1700
Data Index: 7326341 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5703. Min Range: -4.5703
Max Act: 4.3516. Min Act: -0.1700
Data Index: 4640531 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5703. Min Range: -4.5703
Max Act: 4.3516. Min Act: -0.1700
Data Index: 558765 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #19