Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2015 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.6629. Min Range: -2.6629
Max Act: 2.6629. Min Act: -0.1700
Data Index: 5377426 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6629. Min Range: -2.6629
Max Act: 2.6308. Min Act: -0.1700
Data Index: 8029169 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6629. Min Range: -2.6629
Max Act: 2.6469. Min Act: -0.1700
Data Index: 7081003 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6629. Min Range: -2.6629
Max Act: 2.6629. Min Act: -0.1700
Data Index: 6258968 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6629. Min Range: -2.6629
Max Act: 2.6469. Min Act: -0.1700
Data Index: 1728029 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6629. Min Range: -2.6629
Max Act: 2.6469. Min Act: -0.1700
Data Index: 5818947 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6629. Min Range: -2.6629
Max Act: 2.6469. Min Act: -0.1700
Data Index: 298561 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6629. Min Range: -2.6629
Max Act: 2.6469. Min Act: -0.1700
Data Index: 499034 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6629. Min Range: -2.6629
Max Act: 2.6469. Min Act: -0.1700
Data Index: 4489523 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6629. Min Range: -2.6629
Max Act: 2.6629. Min Act: -0.1700
Data Index: 8192555 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6629. Min Range: -2.6629
Max Act: 2.6469. Min Act: -0.1700
Data Index: 7613313 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6629. Min Range: -2.6629
Max Act: 2.6308. Min Act: -0.1700
Data Index: 2629998 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6629. Min Range: -2.6629
Max Act: 2.6469. Min Act: -0.1700
Data Index: 1705458 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6629. Min Range: -2.6629
Max Act: 2.6308. Min Act: -0.1700
Data Index: 6892513 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6629. Min Range: -2.6629
Max Act: 2.6469. Min Act: -0.1700
Data Index: 7062201 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6629. Min Range: -2.6629
Max Act: 2.6308. Min Act: -0.1700
Data Index: 2010474 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6629. Min Range: -2.6629
Max Act: 2.6308. Min Act: -0.1700
Data Index: 336928 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6629. Min Range: -2.6629
Max Act: 2.6308. Min Act: -0.1700
Data Index: 7196155 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6629. Min Range: -2.6629
Max Act: 2.6308. Min Act: -0.1700
Data Index: 7205129 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6629. Min Range: -2.6629
Max Act: 2.6308. Min Act: -0.1700
Data Index: 7423505 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #19