Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2729 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.5843. Min Range: -1.5843
Max Act: 1.5843. Min Act: -0.1699
Data Index: 5567411 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5843. Min Range: -1.5843
Max Act: 1.5756. Min Act: -0.1699
Data Index: 5273759 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5843. Min Range: -1.5843
Max Act: 1.5668. Min Act: -0.1681
Data Index: 2356149 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5843. Min Range: -1.5843
Max Act: 1.5581. Min Act: -0.1681
Data Index: 3203213 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5843. Min Range: -1.5843
Max Act: 1.5668. Min Act: -0.1635
Data Index: 4124518 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5843. Min Range: -1.5843
Max Act: 1.5581. Min Act: -0.1697
Data Index: 1678071 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5843. Min Range: -1.5843
Max Act: 1.5318. Min Act: -0.1698
Data Index: 7628800 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5843. Min Range: -1.5843
Max Act: 1.5230. Min Act: -0.1650
Data Index: 6497661 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5843. Min Range: -1.5843
Max Act: 1.5318. Min Act: -0.1699
Data Index: 3431385 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5843. Min Range: -1.5843
Max Act: 1.5230. Min Act: -0.1657
Data Index: 2605659 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5843. Min Range: -1.5843
Max Act: 1.5230. Min Act: -0.1686
Data Index: 4259479 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5843. Min Range: -1.5843
Max Act: 1.5230. Min Act: -0.1700
Data Index: 5822825 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5843. Min Range: -1.5843
Max Act: 1.5142. Min Act: -0.1700
Data Index: 1273485 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5843. Min Range: -1.5843
Max Act: 1.5055. Min Act: -0.1693
Data Index: 8334708 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5843. Min Range: -1.5843
Max Act: 1.5142. Min Act: -0.1628
Data Index: 3621243 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5843. Min Range: -1.5843
Max Act: 1.5055. Min Act: -0.1700
Data Index: 2904411 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5843. Min Range: -1.5843
Max Act: 1.5055. Min Act: -0.1601
Data Index: 5349252 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5843. Min Range: -1.5843
Max Act: 1.4967. Min Act: -0.1667
Data Index: 2254363 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5843. Min Range: -1.5843
Max Act: 1.5055. Min Act: -0.1562
Data Index: 7143333 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5843. Min Range: -1.5843
Max Act: 1.5055. Min Act: -0.1679
Data Index: 432697 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #19