Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6396 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3653. Min Range: -4.3653
Max Act: 4.3653. Min Act: -0.1700
Data Index: 4893027 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3653. Min Range: -4.3653
Max Act: 4.3341. Min Act: -0.1700
Data Index: 3448488 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3653. Min Range: -4.3653
Max Act: 4.3028. Min Act: -0.1700
Data Index: 691105 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3653. Min Range: -4.3653
Max Act: 4.2403. Min Act: -0.1700
Data Index: 1351568 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3653. Min Range: -4.3653
Max Act: 4.2403. Min Act: -0.1700
Data Index: 2547682 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3653. Min Range: -4.3653
Max Act: 4.2403. Min Act: -0.1700
Data Index: 2848142 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3653. Min Range: -4.3653
Max Act: 4.2091. Min Act: -0.1700
Data Index: 6398749 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3653. Min Range: -4.3653
Max Act: 4.2091. Min Act: -0.1700
Data Index: 5482076 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3653. Min Range: -4.3653
Max Act: 4.2091. Min Act: -0.1700
Data Index: 2397589 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3653. Min Range: -4.3653
Max Act: 4.2091. Min Act: -0.1700
Data Index: 2030028 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3653. Min Range: -4.3653
Max Act: 4.2091. Min Act: -0.1700
Data Index: 559744 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3653. Min Range: -4.3653
Max Act: 4.2091. Min Act: -0.1700
Data Index: 1761021 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3653. Min Range: -4.3653
Max Act: 4.2091. Min Act: -0.1700
Data Index: 7052936 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3653. Min Range: -4.3653
Max Act: 4.1778. Min Act: -0.1700
Data Index: 2209130 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3653. Min Range: -4.3653
Max Act: 4.1778. Min Act: -0.1700
Data Index: 3779966 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3653. Min Range: -4.3653
Max Act: 4.1778. Min Act: -0.1700
Data Index: 4175827 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3653. Min Range: -4.3653
Max Act: 4.1778. Min Act: -0.1700
Data Index: 4284442 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3653. Min Range: -4.3653
Max Act: 4.1778. Min Act: -0.1700
Data Index: 4721687 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3653. Min Range: -4.3653
Max Act: 4.1778. Min Act: -0.1700
Data Index: 811701 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3653. Min Range: -4.3653
Max Act: 4.1778. Min Act: -0.1700
Data Index: 2933878 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #19