Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 781 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.8518. Min Range: -8.8518
Max Act: 8.8518. Min Act: -0.1700
Data Index: 1145873 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8518. Min Range: -8.8518
Max Act: 8.6643. Min Act: -0.1700
Data Index: 6410079 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8518. Min Range: -8.8518
Max Act: 8.6643. Min Act: -0.1700
Data Index: 6852121 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8518. Min Range: -8.8518
Max Act: 8.6018. Min Act: -0.1700
Data Index: 2357696 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8518. Min Range: -8.8518
Max Act: 8.6018. Min Act: -0.1700
Data Index: 973528 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8518. Min Range: -8.8518
Max Act: 8.5393. Min Act: -0.1700
Data Index: 691590 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8518. Min Range: -8.8518
Max Act: 8.5393. Min Act: -0.1700
Data Index: 4023425 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8518. Min Range: -8.8518
Max Act: 8.4143. Min Act: -0.1700
Data Index: 381329 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8518. Min Range: -8.8518
Max Act: 8.4768. Min Act: -0.1700
Data Index: 6914602 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8518. Min Range: -8.8518
Max Act: 8.4143. Min Act: -0.1700
Data Index: 8627702 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8518. Min Range: -8.8518
Max Act: 8.4143. Min Act: -0.1700
Data Index: 4803392 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8518. Min Range: -8.8518
Max Act: 8.4143. Min Act: -0.1700
Data Index: 8012731 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8518. Min Range: -8.8518
Max Act: 8.4143. Min Act: -0.1700
Data Index: 7268534 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8518. Min Range: -8.8518
Max Act: 8.3518. Min Act: -0.1700
Data Index: 4727795 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8518. Min Range: -8.8518
Max Act: 8.3518. Min Act: -0.1700
Data Index: 1946062 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8518. Min Range: -8.8518
Max Act: 8.3518. Min Act: -0.1700
Data Index: 3959913 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8518. Min Range: -8.8518
Max Act: 8.3518. Min Act: -0.1700
Data Index: 7672133 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8518. Min Range: -8.8518
Max Act: 8.3518. Min Act: -0.1700
Data Index: 1361736 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8518. Min Range: -8.8518
Max Act: 8.3518. Min Act: -0.1700
Data Index: 6777418 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8518. Min Range: -8.8518
Max Act: 8.2893. Min Act: -0.1700
Data Index: 7616209 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #19