Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1142 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.0671. Min Range: -6.0671
Max Act: 6.0671. Min Act: -0.1700
Data Index: 6912444 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0671. Min Range: -6.0671
Max Act: 6.0046. Min Act: -0.1693
Data Index: 2492303 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0671. Min Range: -6.0671
Max Act: 5.9421. Min Act: -0.1700
Data Index: 731488 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0671. Min Range: -6.0671
Max Act: 5.8796. Min Act: -0.1700
Data Index: 5460705 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0671. Min Range: -6.0671
Max Act: 5.8484. Min Act: -0.1700
Data Index: 3560475 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0671. Min Range: -6.0671
Max Act: 5.8484. Min Act: -0.1700
Data Index: 3587292 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0671. Min Range: -6.0671
Max Act: 5.8484. Min Act: -0.1700
Data Index: 5459616 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0671. Min Range: -6.0671
Max Act: 5.8171. Min Act: -0.1700
Data Index: 4808342 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0671. Min Range: -6.0671
Max Act: 5.7859. Min Act: -0.1700
Data Index: 7943722 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0671. Min Range: -6.0671
Max Act: 5.7859. Min Act: -0.1687
Data Index: 7122092 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0671. Min Range: -6.0671
Max Act: 5.7859. Min Act: -0.1698
Data Index: 5777314 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0671. Min Range: -6.0671
Max Act: 5.7234. Min Act: -0.1700
Data Index: 2560348 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0671. Min Range: -6.0671
Max Act: 5.7546. Min Act: -0.1700
Data Index: 7514370 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0671. Min Range: -6.0671
Max Act: 5.7234. Min Act: -0.1700
Data Index: 702804 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0671. Min Range: -6.0671
Max Act: 5.7546. Min Act: -0.1698
Data Index: 1372696 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0671. Min Range: -6.0671
Max Act: 5.7546. Min Act: -0.1700
Data Index: 6956751 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0671. Min Range: -6.0671
Max Act: 5.7546. Min Act: -0.1694
Data Index: 8516844 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0671. Min Range: -6.0671
Max Act: 5.7546. Min Act: -0.1700
Data Index: 6297861 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0671. Min Range: -6.0671
Max Act: 5.7546. Min Act: -0.1700
Data Index: 1586034 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0671. Min Range: -6.0671
Max Act: 5.7546. Min Act: -0.1700
Data Index: 8724308 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #19