Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4249 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1314. Min Range: -5.1314
Max Act: 5.1314. Min Act: -0.1700
Data Index: 6807491 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1314. Min Range: -5.1314
Max Act: 5.1001. Min Act: -0.1700
Data Index: 1696256 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1314. Min Range: -5.1314
Max Act: 5.0376. Min Act: -0.1700
Data Index: 1050745 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1314. Min Range: -5.1314
Max Act: 5.0376. Min Act: -0.1700
Data Index: 6996430 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1314. Min Range: -5.1314
Max Act: 5.0064. Min Act: -0.1700
Data Index: 4982764 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1314. Min Range: -5.1314
Max Act: 4.9751. Min Act: -0.1700
Data Index: 2180490 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1314. Min Range: -5.1314
Max Act: 4.9751. Min Act: -0.1700
Data Index: 4061709 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1314. Min Range: -5.1314
Max Act: 4.9751. Min Act: -0.1700
Data Index: 4691194 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1314. Min Range: -5.1314
Max Act: 4.9751. Min Act: -0.1700
Data Index: 2378507 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1314. Min Range: -5.1314
Max Act: 4.9751. Min Act: -0.1700
Data Index: 3236001 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1314. Min Range: -5.1314
Max Act: 4.9751. Min Act: -0.1700
Data Index: 2540087 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1314. Min Range: -5.1314
Max Act: 4.9751. Min Act: -0.1700
Data Index: 6721092 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1314. Min Range: -5.1314
Max Act: 4.9751. Min Act: -0.1700
Data Index: 7221972 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1314. Min Range: -5.1314
Max Act: 4.9439. Min Act: -0.1700
Data Index: 4817399 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1314. Min Range: -5.1314
Max Act: 4.9439. Min Act: -0.1700
Data Index: 636685 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1314. Min Range: -5.1314
Max Act: 4.9439. Min Act: -0.1700
Data Index: 2616622 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1314. Min Range: -5.1314
Max Act: 4.9439. Min Act: -0.1700
Data Index: 5859974 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1314. Min Range: -5.1314
Max Act: 4.9126. Min Act: -0.1700
Data Index: 6127818 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1314. Min Range: -5.1314
Max Act: 4.9439. Min Act: -0.1700
Data Index: 2915733 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1314. Min Range: -5.1314
Max Act: 4.9439. Min Act: -0.1700
Data Index: 6791426 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19