Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4187 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9812. Min Range: -4.9812
Max Act: 4.9812. Min Act: -0.1700
Data Index: 7983725 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9812. Min Range: -4.9812
Max Act: 4.9812. Min Act: -0.1700
Data Index: 43561 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9812. Min Range: -4.9812
Max Act: 4.9812. Min Act: -0.1700
Data Index: 3279546 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9812. Min Range: -4.9812
Max Act: 4.9187. Min Act: -0.1700
Data Index: 2105503 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9812. Min Range: -4.9812
Max Act: 4.9500. Min Act: -0.1700
Data Index: 2043641 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9812. Min Range: -4.9812
Max Act: 4.8875. Min Act: -0.1700
Data Index: 6763918 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9812. Min Range: -4.9812
Max Act: 4.8250. Min Act: -0.1700
Data Index: 7599765 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9812. Min Range: -4.9812
Max Act: 4.7937. Min Act: -0.1700
Data Index: 6328797 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9812. Min Range: -4.9812
Max Act: 4.7937. Min Act: -0.1700
Data Index: 1731409 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9812. Min Range: -4.9812
Max Act: 4.7625. Min Act: -0.1700
Data Index: 6644146 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9812. Min Range: -4.9812
Max Act: 4.7312. Min Act: -0.1700
Data Index: 3661120 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9812. Min Range: -4.9812
Max Act: 4.7000. Min Act: -0.1700
Data Index: 8608191 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9812. Min Range: -4.9812
Max Act: 4.6687. Min Act: -0.1700
Data Index: 1805985 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9812. Min Range: -4.9812
Max Act: 4.6687. Min Act: -0.1700
Data Index: 2797288 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9812. Min Range: -4.9812
Max Act: 4.7000. Min Act: -0.1700
Data Index: 64787 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9812. Min Range: -4.9812
Max Act: 4.7000. Min Act: -0.1700
Data Index: 4340553 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9812. Min Range: -4.9812
Max Act: 4.7000. Min Act: -0.1700
Data Index: 1704837 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9812. Min Range: -4.9812
Max Act: 4.6687. Min Act: -0.1700
Data Index: 7788578 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9812. Min Range: -4.9812
Max Act: 4.6375. Min Act: -0.1700
Data Index: 2886587 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9812. Min Range: -4.9812
Max Act: 4.6687. Min Act: -0.1700
Data Index: 4934958 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #19