Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3962 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9619. Min Range: -3.9619
Max Act: 3.9619. Min Act: -0.1700
Data Index: 6896505 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9619. Min Range: -3.9619
Max Act: 3.9306. Min Act: -0.1700
Data Index: 7901517 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9619. Min Range: -3.9619
Max Act: 3.8993. Min Act: -0.1700
Data Index: 1200118 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9619. Min Range: -3.9619
Max Act: 3.8993. Min Act: -0.1700
Data Index: 5370527 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9619. Min Range: -3.9619
Max Act: 3.8368. Min Act: -0.1700
Data Index: 7801364 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9619. Min Range: -3.9619
Max Act: 3.7742. Min Act: -0.1700
Data Index: 5961281 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9619. Min Range: -3.9619
Max Act: 3.7586. Min Act: -0.1700
Data Index: 8601052 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9619. Min Range: -3.9619
Max Act: 3.7586. Min Act: -0.1700
Data Index: 8276510 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9619. Min Range: -3.9619
Max Act: 3.6804. Min Act: -0.1700
Data Index: 2253168 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9619. Min Range: -3.9619
Max Act: 3.6804. Min Act: -0.1700
Data Index: 6914376 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9619. Min Range: -3.9619
Max Act: 3.6804. Min Act: -0.1700
Data Index: 7447536 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9619. Min Range: -3.9619
Max Act: 3.6178. Min Act: -0.1700
Data Index: 281216 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9619. Min Range: -3.9619
Max Act: 3.6022. Min Act: -0.1700
Data Index: 4854335 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9619. Min Range: -3.9619
Max Act: 3.6178. Min Act: -0.1700
Data Index: 7872121 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9619. Min Range: -3.9619
Max Act: 3.6178. Min Act: -0.1700
Data Index: 898600 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9619. Min Range: -3.9619
Max Act: 3.6022. Min Act: -0.1700
Data Index: 4879534 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9619. Min Range: -3.9619
Max Act: 3.5865. Min Act: -0.1700
Data Index: 5826438 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9619. Min Range: -3.9619
Max Act: 3.5865. Min Act: -0.1700
Data Index: 8115391 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9619. Min Range: -3.9619
Max Act: 3.5865. Min Act: -0.1700
Data Index: 8155571 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9619. Min Range: -3.9619
Max Act: 3.5865. Min Act: -0.1700
Data Index: 671141 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #19