Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1531 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.1620. Min Range: -3.1620
Max Act: 3.1620. Min Act: -0.1700
Data Index: 2082071 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1620. Min Range: -3.1620
Max Act: 3.1620. Min Act: -0.1700
Data Index: 3522249 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1620. Min Range: -3.1620
Max Act: 3.1620. Min Act: -0.1700
Data Index: 419148 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1620. Min Range: -3.1620
Max Act: 3.1620. Min Act: -0.1700
Data Index: 5703118 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1620. Min Range: -3.1620
Max Act: 3.1463. Min Act: -0.1700
Data Index: 3568959 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1620. Min Range: -3.1620
Max Act: 3.1463. Min Act: -0.1700
Data Index: 1370473 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1620. Min Range: -3.1620
Max Act: 3.0990. Min Act: -0.1700
Data Index: 4896604 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1620. Min Range: -3.1620
Max Act: 3.0990. Min Act: -0.1700
Data Index: 5045524 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1620. Min Range: -3.1620
Max Act: 3.0990. Min Act: -0.1700
Data Index: 6849149 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1620. Min Range: -3.1620
Max Act: 3.0990. Min Act: -0.1700
Data Index: 6640621 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1620. Min Range: -3.1620
Max Act: 3.0675. Min Act: -0.1700
Data Index: 7623536 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1620. Min Range: -3.1620
Max Act: 3.0675. Min Act: -0.1700
Data Index: 8826463 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1620. Min Range: -3.1620
Max Act: 3.0359. Min Act: -0.1700
Data Index: 1276261 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1620. Min Range: -3.1620
Max Act: 3.0517. Min Act: -0.1700
Data Index: 7755930 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1620. Min Range: -3.1620
Max Act: 3.0359. Min Act: -0.1700
Data Index: 1280271 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1620. Min Range: -3.1620
Max Act: 3.0359. Min Act: -0.1700
Data Index: 2376392 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1620. Min Range: -3.1620
Max Act: 3.0201. Min Act: -0.1700
Data Index: 7345458 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1620. Min Range: -3.1620
Max Act: 3.0359. Min Act: -0.1700
Data Index: 7274016 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1620. Min Range: -3.1620
Max Act: 3.0201. Min Act: -0.1700
Data Index: 7457779 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1620. Min Range: -3.1620
Max Act: 3.0201. Min Act: -0.1700
Data Index: 2054006 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #19