Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2027 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.4848. Min Range: -3.4848
Max Act: 3.4848. Min Act: -0.1700
Data Index: 6942078 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4848. Min Range: -3.4848
Max Act: 3.4848. Min Act: -0.1700
Data Index: 84454 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4848. Min Range: -3.4848
Max Act: 3.4848. Min Act: -0.1700
Data Index: 5686022 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4848. Min Range: -3.4848
Max Act: 3.4848. Min Act: -0.1700
Data Index: 5464484 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4848. Min Range: -3.4848
Max Act: 3.4848. Min Act: -0.1700
Data Index: 5436196 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4848. Min Range: -3.4848
Max Act: 3.4848. Min Act: -0.1700
Data Index: 749855 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4848. Min Range: -3.4848
Max Act: 3.4848. Min Act: -0.1700
Data Index: 7593752 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4848. Min Range: -3.4848
Max Act: 3.4848. Min Act: -0.1700
Data Index: 6074088 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4848. Min Range: -3.4848
Max Act: 3.4848. Min Act: -0.1700
Data Index: 2765519 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4848. Min Range: -3.4848
Max Act: 3.4848. Min Act: -0.1700
Data Index: 2242675 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4848. Min Range: -3.4848
Max Act: 3.4848. Min Act: -0.1700
Data Index: 670572 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4848. Min Range: -3.4848
Max Act: 3.4848. Min Act: -0.1700
Data Index: 381562 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4848. Min Range: -3.4848
Max Act: 3.4848. Min Act: -0.1699
Data Index: 6575535 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4848. Min Range: -3.4848
Max Act: 3.4848. Min Act: -0.1700
Data Index: 1849827 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4848. Min Range: -3.4848
Max Act: 3.4848. Min Act: -0.1700
Data Index: 1570636 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4848. Min Range: -3.4848
Max Act: 3.4848. Min Act: -0.1700
Data Index: 1319856 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4848. Min Range: -3.4848
Max Act: 3.4848. Min Act: -0.1700
Data Index: 1104015 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4848. Min Range: -3.4848
Max Act: 3.4534. Min Act: -0.1700
Data Index: 4820332 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4848. Min Range: -3.4848
Max Act: 3.4534. Min Act: -0.1700
Data Index: 5224917 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4848. Min Range: -3.4848
Max Act: 3.4534. Min Act: -0.1700
Data Index: 5905602 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19