Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2959 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.1653. Min Range: -1.1653
Max Act: 1.1653. Min Act: -0.1700
Data Index: 1533804 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.1653. Min Range: -1.1653
Max Act: 1.1478. Min Act: -0.1700
Data Index: 580135 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.1653. Min Range: -1.1653
Max Act: 1.1302. Min Act: -0.1700
Data Index: 3759792 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.1653. Min Range: -1.1653
Max Act: 1.1302. Min Act: -0.1696
Data Index: 1267076 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.1653. Min Range: -1.1653
Max Act: 1.1127. Min Act: -0.1696
Data Index: 5496074 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.1653. Min Range: -1.1653
Max Act: 1.0951. Min Act: -0.1699
Data Index: 6373501 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.1653. Min Range: -1.1653
Max Act: 1.0776. Min Act: -0.1696
Data Index: 822165 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.1653. Min Range: -1.1653
Max Act: 1.0602. Min Act: -0.1700
Data Index: 1996581 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.1653. Min Range: -1.1653
Max Act: 1.0602. Min Act: -0.1696
Data Index: 594884 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.1653. Min Range: -1.1653
Max Act: 1.0602. Min Act: -0.1696
Data Index: 282493 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.1653. Min Range: -1.1653
Max Act: 1.0602. Min Act: -0.1696
Data Index: 2601983 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.1653. Min Range: -1.1653
Max Act: 1.0602. Min Act: -0.1696
Data Index: 2655969 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.1653. Min Range: -1.1653
Max Act: 1.0602. Min Act: -0.1696
Data Index: 2929367 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.1653. Min Range: -1.1653
Max Act: 1.0602. Min Act: -0.1698
Data Index: 634307 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.1653. Min Range: -1.1653
Max Act: 1.0602. Min Act: -0.1697
Data Index: 3316364 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.1653. Min Range: -1.1653
Max Act: 1.0602. Min Act: -0.1700
Data Index: 3183563 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.1653. Min Range: -1.1653
Max Act: 1.0602. Min Act: -0.1696
Data Index: 1110624 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.1653. Min Range: -1.1653
Max Act: 1.0602. Min Act: -0.1696
Data Index: 2415278 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.1653. Min Range: -1.1653
Max Act: 1.0602. Min Act: -0.1696
Data Index: 2757019 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.1653. Min Range: -1.1653
Max Act: 1.0602. Min Act: -0.1696
Data Index: 2508527 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19