Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3318 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.0077. Min Range: -2.0077
Max Act: 2.0077. Min Act: -0.1700
Data Index: 7983524 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0077. Min Range: -2.0077
Max Act: 1.9229. Min Act: -0.1700
Data Index: 7983512 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0077. Min Range: -2.0077
Max Act: 1.8717. Min Act: -0.1700
Data Index: 4725906 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0077. Min Range: -2.0077
Max Act: 1.8717. Min Act: -0.1700
Data Index: 457307 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0077. Min Range: -2.0077
Max Act: 1.8546. Min Act: -0.1700
Data Index: 106287 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0077. Min Range: -2.0077
Max Act: 1.8717. Min Act: -0.1700
Data Index: 339383 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0077. Min Range: -2.0077
Max Act: 1.8717. Min Act: -0.1700
Data Index: 752900 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0077. Min Range: -2.0077
Max Act: 1.8546. Min Act: -0.1700
Data Index: 4861568 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0077. Min Range: -2.0077
Max Act: 1.8203. Min Act: -0.1700
Data Index: 5160323 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0077. Min Range: -2.0077
Max Act: 1.8203. Min Act: -0.1700
Data Index: 5741682 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0077. Min Range: -2.0077
Max Act: 1.8203. Min Act: -0.1700
Data Index: 7762585 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0077. Min Range: -2.0077
Max Act: 1.8375. Min Act: -0.1700
Data Index: 8230006 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0077. Min Range: -2.0077
Max Act: 1.8203. Min Act: -0.1700
Data Index: 7320578 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0077. Min Range: -2.0077
Max Act: 1.8375. Min Act: -0.1700
Data Index: 4725911 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0077. Min Range: -2.0077
Max Act: 1.8031. Min Act: -0.1695
Data Index: 1894429 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0077. Min Range: -2.0077
Max Act: 1.7859. Min Act: -0.1700
Data Index: 5940438 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0077. Min Range: -2.0077
Max Act: 1.7687. Min Act: -0.1700
Data Index: 4725913 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0077. Min Range: -2.0077
Max Act: 1.7687. Min Act: -0.1700
Data Index: 2830030 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0077. Min Range: -2.0077
Max Act: 1.7514. Min Act: -0.1695
Data Index: 8267812 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0077. Min Range: -2.0077
Max Act: 1.7687. Min Act: -0.1700
Data Index: 4913811 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #19