Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4898 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2535. Min Range: -4.2535
Max Act: 4.2535. Min Act: -0.1700
Data Index: 7344711 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2535. Min Range: -4.2535
Max Act: 4.0973. Min Act: -0.1700
Data Index: 6497706 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2535. Min Range: -4.2535
Max Act: 3.9410. Min Act: -0.1700
Data Index: 1037431 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2535. Min Range: -4.2535
Max Act: 3.8472. Min Act: -0.1700
Data Index: 6978855 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2535. Min Range: -4.2535
Max Act: 3.7846. Min Act: -0.1700
Data Index: 2723185 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2535. Min Range: -4.2535
Max Act: 3.7533. Min Act: -0.1700
Data Index: 2368264 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2535. Min Range: -4.2535
Max Act: 3.7221. Min Act: -0.1700
Data Index: 6497704 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2535. Min Range: -4.2535
Max Act: 3.7377. Min Act: -0.1700
Data Index: 8575249 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2535. Min Range: -4.2535
Max Act: 3.7064. Min Act: -0.1700
Data Index: 6497705 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2535. Min Range: -4.2535
Max Act: 3.7064. Min Act: -0.1700
Data Index: 6497703 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2535. Min Range: -4.2535
Max Act: 3.6751. Min Act: -0.1700
Data Index: 1755763 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2535. Min Range: -4.2535
Max Act: 3.6595. Min Act: -0.1700
Data Index: 5861934 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2535. Min Range: -4.2535
Max Act: 3.6595. Min Act: -0.1700
Data Index: 656998 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2535. Min Range: -4.2535
Max Act: 3.6282. Min Act: -0.1700
Data Index: 6252981 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2535. Min Range: -4.2535
Max Act: 3.5812. Min Act: -0.1700
Data Index: 351772 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2535. Min Range: -4.2535
Max Act: 3.5656. Min Act: -0.1700
Data Index: 3904401 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2535. Min Range: -4.2535
Max Act: 3.5499. Min Act: -0.1700
Data Index: 3274666 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2535. Min Range: -4.2535
Max Act: 3.5499. Min Act: -0.1700
Data Index: 2899471 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2535. Min Range: -4.2535
Max Act: 3.5343. Min Act: -0.1700
Data Index: 1473077 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2535. Min Range: -4.2535
Max Act: 3.5186. Min Act: -0.1700
Data Index: 8035004 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #19