Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5800 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2479. Min Range: -5.2479
Max Act: 5.2479. Min Act: -0.1700
Data Index: 5867775 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2479. Min Range: -5.2479
Max Act: 5.2167. Min Act: -0.1700
Data Index: 5825275 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2479. Min Range: -5.2479
Max Act: 5.0604. Min Act: -0.1700
Data Index: 2752833 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2479. Min Range: -5.2479
Max Act: 5.0917. Min Act: -0.1700
Data Index: 4838669 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2479. Min Range: -5.2479
Max Act: 4.9979. Min Act: -0.1700
Data Index: 5105110 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2479. Min Range: -5.2479
Max Act: 4.9667. Min Act: -0.1700
Data Index: 3210945 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2479. Min Range: -5.2479
Max Act: 4.9667. Min Act: -0.1700
Data Index: 7462636 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2479. Min Range: -5.2479
Max Act: 4.9354. Min Act: -0.1700
Data Index: 4291982 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2479. Min Range: -5.2479
Max Act: 4.9354. Min Act: -0.1700
Data Index: 1807210 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2479. Min Range: -5.2479
Max Act: 4.9354. Min Act: -0.1700
Data Index: 8334531 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2479. Min Range: -5.2479
Max Act: 4.9354. Min Act: -0.1700
Data Index: 1612379 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2479. Min Range: -5.2479
Max Act: 4.9354. Min Act: -0.1700
Data Index: 1599763 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2479. Min Range: -5.2479
Max Act: 4.9042. Min Act: -0.1700
Data Index: 1981225 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2479. Min Range: -5.2479
Max Act: 4.9042. Min Act: -0.1700
Data Index: 7306879 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2479. Min Range: -5.2479
Max Act: 4.9042. Min Act: -0.1700
Data Index: 7594837 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2479. Min Range: -5.2479
Max Act: 4.9042. Min Act: -0.1700
Data Index: 8000104 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2479. Min Range: -5.2479
Max Act: 4.9354. Min Act: -0.1700
Data Index: 8007775 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2479. Min Range: -5.2479
Max Act: 4.8729. Min Act: -0.1700
Data Index: 3219993 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2479. Min Range: -5.2479
Max Act: 4.8729. Min Act: -0.1700
Data Index: 4477851 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2479. Min Range: -5.2479
Max Act: 4.8729. Min Act: -0.1700
Data Index: 2000705 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #19