Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4836 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7419. Min Range: -3.7419
Max Act: 3.7419. Min Act: -0.1700
Data Index: 546220 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7419. Min Range: -3.7419
Max Act: 3.6950. Min Act: -0.1700
Data Index: 2914917 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7419. Min Range: -3.7419
Max Act: 3.6167. Min Act: -0.1700
Data Index: 2914914 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7419. Min Range: -3.7419
Max Act: 3.6167. Min Act: -0.1700
Data Index: 2797705 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7419. Min Range: -3.7419
Max Act: 3.5854. Min Act: -0.1700
Data Index: 4700133 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7419. Min Range: -3.7419
Max Act: 3.6011. Min Act: -0.1700
Data Index: 6121727 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7419. Min Range: -3.7419
Max Act: 3.5541. Min Act: -0.1700
Data Index: 1924158 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7419. Min Range: -3.7419
Max Act: 3.5385. Min Act: -0.1700
Data Index: 3069400 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7419. Min Range: -3.7419
Max Act: 3.5385. Min Act: -0.1700
Data Index: 5873433 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7419. Min Range: -3.7419
Max Act: 3.5385. Min Act: -0.1700
Data Index: 190275 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7419. Min Range: -3.7419
Max Act: 3.5228. Min Act: -0.1700
Data Index: 5873421 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7419. Min Range: -3.7419
Max Act: 3.4915. Min Act: -0.1700
Data Index: 5610998 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7419. Min Range: -3.7419
Max Act: 3.4915. Min Act: -0.1700
Data Index: 4958430 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7419. Min Range: -3.7419
Max Act: 3.4758. Min Act: -0.1700
Data Index: 151495 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7419. Min Range: -3.7419
Max Act: 3.4915. Min Act: -0.1700
Data Index: 844443 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7419. Min Range: -3.7419
Max Act: 3.4758. Min Act: -0.1700
Data Index: 6697496 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7419. Min Range: -3.7419
Max Act: 3.4758. Min Act: -0.1700
Data Index: 3262971 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7419. Min Range: -3.7419
Max Act: 3.4601. Min Act: -0.1700
Data Index: 3868331 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7419. Min Range: -3.7419
Max Act: 3.4758. Min Act: -0.1700
Data Index: 5873439 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7419. Min Range: -3.7419
Max Act: 3.4445. Min Act: -0.1700
Data Index: 5610995 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #19