Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3985 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8516. Min Range: -6.8516
Max Act: 6.8516. Min Act: -0.1700
Data Index: 8205659 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8516. Min Range: -6.8516
Max Act: 6.8203. Min Act: -0.1700
Data Index: 5758612 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8516. Min Range: -6.8516
Max Act: 6.7578. Min Act: -0.1700
Data Index: 8197177 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8516. Min Range: -6.8516
Max Act: 6.7266. Min Act: -0.1700
Data Index: 1512560 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8516. Min Range: -6.8516
Max Act: 6.6953. Min Act: -0.1700
Data Index: 7731449 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8516. Min Range: -6.8516
Max Act: 6.6641. Min Act: -0.1700
Data Index: 2983286 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8516. Min Range: -6.8516
Max Act: 6.6328. Min Act: -0.1700
Data Index: 2623969 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8516. Min Range: -6.8516
Max Act: 6.6016. Min Act: -0.1700
Data Index: 2250262 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8516. Min Range: -6.8516
Max Act: 6.5703. Min Act: -0.1700
Data Index: 6484299 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8516. Min Range: -6.8516
Max Act: 6.5703. Min Act: -0.1700
Data Index: 8530662 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8516. Min Range: -6.8516
Max Act: 6.5391. Min Act: -0.1700
Data Index: 638772 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8516. Min Range: -6.8516
Max Act: 6.5391. Min Act: -0.1700
Data Index: 5378618 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8516. Min Range: -6.8516
Max Act: 6.5391. Min Act: -0.1700
Data Index: 425302 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8516. Min Range: -6.8516
Max Act: 6.5078. Min Act: -0.1700
Data Index: 1589495 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8516. Min Range: -6.8516
Max Act: 6.5078. Min Act: -0.1700
Data Index: 2357645 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8516. Min Range: -6.8516
Max Act: 6.5078. Min Act: -0.1700
Data Index: 7636833 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8516. Min Range: -6.8516
Max Act: 6.5078. Min Act: -0.1700
Data Index: 1589478 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8516. Min Range: -6.8516
Max Act: 6.4453. Min Act: -0.1700
Data Index: 7940186 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8516. Min Range: -6.8516
Max Act: 6.3203. Min Act: -0.1700
Data Index: 1899800 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8516. Min Range: -6.8516
Max Act: 6.3516. Min Act: -0.1700
Data Index: 2765401 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #19