Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2533 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.0659. Min Range: -3.0659
Max Act: 3.0659. Min Act: -0.1700
Data Index: 2396091 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0659. Min Range: -3.0659
Max Act: 2.9869. Min Act: -0.1700
Data Index: 7512931 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0659. Min Range: -3.0659
Max Act: 2.9553. Min Act: -0.1700
Data Index: 6600085 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0659. Min Range: -3.0659
Max Act: 2.9553. Min Act: -0.1700
Data Index: 4035562 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0659. Min Range: -3.0659
Max Act: 2.9394. Min Act: -0.1700
Data Index: 8716772 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0659. Min Range: -3.0659
Max Act: 2.9236. Min Act: -0.1700
Data Index: 8326663 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0659. Min Range: -3.0659
Max Act: 2.9078. Min Act: -0.1700
Data Index: 2310568 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0659. Min Range: -3.0659
Max Act: 2.9078. Min Act: -0.1700
Data Index: 715956 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0659. Min Range: -3.0659
Max Act: 2.8919. Min Act: -0.1700
Data Index: 6683133 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0659. Min Range: -3.0659
Max Act: 2.8760. Min Act: -0.1700
Data Index: 6765400 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0659. Min Range: -3.0659
Max Act: 2.8919. Min Act: -0.1700
Data Index: 6600082 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0659. Min Range: -3.0659
Max Act: 2.8760. Min Act: -0.1700
Data Index: 8037927 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0659. Min Range: -3.0659
Max Act: 2.8919. Min Act: -0.1700
Data Index: 1808137 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0659. Min Range: -3.0659
Max Act: 2.8760. Min Act: -0.1700
Data Index: 5092276 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0659. Min Range: -3.0659
Max Act: 2.8760. Min Act: -0.1700
Data Index: 5244608 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0659. Min Range: -3.0659
Max Act: 2.8602. Min Act: -0.1700
Data Index: 61575 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0659. Min Range: -3.0659
Max Act: 2.8760. Min Act: -0.1700
Data Index: 4075097 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0659. Min Range: -3.0659
Max Act: 2.8602. Min Act: -0.1700
Data Index: 3485797 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0659. Min Range: -3.0659
Max Act: 2.8602. Min Act: -0.1700
Data Index: 5595137 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0659. Min Range: -3.0659
Max Act: 2.8602. Min Act: -0.1700
Data Index: 5991951 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #19