Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2239 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9941. Min Range: -3.9941
Max Act: 3.9941. Min Act: -0.1700
Data Index: 7917150 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9941. Min Range: -3.9941
Max Act: 3.9629. Min Act: -0.1700
Data Index: 1302650 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9941. Min Range: -3.9941
Max Act: 3.8065. Min Act: -0.1700
Data Index: 7846097 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9941. Min Range: -3.9941
Max Act: 3.7753. Min Act: -0.1700
Data Index: 5547719 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9941. Min Range: -3.9941
Max Act: 3.7440. Min Act: -0.1700
Data Index: 3182434 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9941. Min Range: -3.9941
Max Act: 3.6814. Min Act: -0.1700
Data Index: 818219 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9941. Min Range: -3.9941
Max Act: 3.6971. Min Act: -0.1700
Data Index: 998872 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9941. Min Range: -3.9941
Max Act: 3.6658. Min Act: -0.1700
Data Index: 2996295 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9941. Min Range: -3.9941
Max Act: 3.6345. Min Act: -0.1700
Data Index: 4956621 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9941. Min Range: -3.9941
Max Act: 3.6501. Min Act: -0.1700
Data Index: 6306383 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9941. Min Range: -3.9941
Max Act: 3.5875. Min Act: -0.1700
Data Index: 7216609 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9941. Min Range: -3.9941
Max Act: 3.6032. Min Act: -0.1700
Data Index: 891606 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9941. Min Range: -3.9941
Max Act: 3.5406. Min Act: -0.1700
Data Index: 8571780 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9941. Min Range: -3.9941
Max Act: 3.5719. Min Act: -0.1700
Data Index: 561808 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9941. Min Range: -3.9941
Max Act: 3.6188. Min Act: -0.1700
Data Index: 6131820 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9941. Min Range: -3.9941
Max Act: 3.5406. Min Act: -0.1700
Data Index: 4309728 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9941. Min Range: -3.9941
Max Act: 3.5406. Min Act: -0.1700
Data Index: 781216 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9941. Min Range: -3.9941
Max Act: 3.5092. Min Act: -0.1700
Data Index: 1302646 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9941. Min Range: -3.9941
Max Act: 3.5249. Min Act: -0.1700
Data Index: 415330 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9941. Min Range: -3.9941
Max Act: 3.5092. Min Act: -0.1700
Data Index: 8433592 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #19