Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4538 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.3449. Min Range: -2.3449
Max Act: 2.3449. Min Act: -0.1700
Data Index: 4807957 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3449. Min Range: -2.3449
Max Act: 2.2957. Min Act: -0.1700
Data Index: 2904932 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3449. Min Range: -2.3449
Max Act: 2.1466. Min Act: -0.1700
Data Index: 6638687 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3449. Min Range: -2.3449
Max Act: 2.0964. Min Act: -0.1699
Data Index: 5556967 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3449. Min Range: -2.3449
Max Act: 2.0629. Min Act: -0.1700
Data Index: 3259401 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3449. Min Range: -2.3449
Max Act: 2.0629. Min Act: -0.1700
Data Index: 5986450 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3449. Min Range: -2.3449
Max Act: 2.0629. Min Act: -0.1700
Data Index: 6974440 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3449. Min Range: -2.3449
Max Act: 2.0461. Min Act: -0.1700
Data Index: 498431 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3449. Min Range: -2.3449
Max Act: 2.0461. Min Act: -0.1700
Data Index: 422608 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3449. Min Range: -2.3449
Max Act: 2.0461. Min Act: -0.1700
Data Index: 5191244 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3449. Min Range: -2.3449
Max Act: 2.0124. Min Act: -0.1700
Data Index: 4502596 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3449. Min Range: -2.3449
Max Act: 2.0124. Min Act: -0.1700
Data Index: 2061951 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3449. Min Range: -2.3449
Max Act: 1.9955. Min Act: -0.1700
Data Index: 2447798 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3449. Min Range: -2.3449
Max Act: 1.9616. Min Act: -0.1700
Data Index: 490154 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3449. Min Range: -2.3449
Max Act: 1.9786. Min Act: -0.1700
Data Index: 1248620 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3449. Min Range: -2.3449
Max Act: 1.9616. Min Act: -0.1700
Data Index: 6201358 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3449. Min Range: -2.3449
Max Act: 1.9786. Min Act: -0.1700
Data Index: 3640876 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3449. Min Range: -2.3449
Max Act: 1.9616. Min Act: -0.1700
Data Index: 6306186 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3449. Min Range: -2.3449
Max Act: 1.9446. Min Act: -0.1700
Data Index: 5729740 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3449. Min Range: -2.3449
Max Act: 1.9616. Min Act: -0.1700
Data Index: 3346974 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #19