Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4181 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.2965. Min Range: -7.2965
Max Act: 7.2965. Min Act: -0.1700
Data Index: 817747 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2965. Min Range: -7.2965
Max Act: 7.1090. Min Act: -0.1700
Data Index: 4729762 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2965. Min Range: -7.2965
Max Act: 7.1403. Min Act: -0.1700
Data Index: 1112148 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2965. Min Range: -7.2965
Max Act: 6.9840. Min Act: -0.1696
Data Index: 3916971 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2965. Min Range: -7.2965
Max Act: 6.8903. Min Act: -0.1700
Data Index: 3704022 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2965. Min Range: -7.2965
Max Act: 6.8590. Min Act: -0.1661
Data Index: 1555290 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2965. Min Range: -7.2965
Max Act: 6.8903. Min Act: -0.1700
Data Index: 201913 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2965. Min Range: -7.2965
Max Act: 6.8590. Min Act: -0.1700
Data Index: 408893 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2965. Min Range: -7.2965
Max Act: 6.8590. Min Act: -0.1700
Data Index: 2492798 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2965. Min Range: -7.2965
Max Act: 6.8278. Min Act: -0.1699
Data Index: 6559251 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2965. Min Range: -7.2965
Max Act: 6.7965. Min Act: -0.1700
Data Index: 5789545 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2965. Min Range: -7.2965
Max Act: 6.7965. Min Act: -0.1700
Data Index: 5273115 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2965. Min Range: -7.2965
Max Act: 6.7965. Min Act: -0.1698
Data Index: 5591538 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2965. Min Range: -7.2965
Max Act: 6.7965. Min Act: -0.1700
Data Index: 8179643 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2965. Min Range: -7.2965
Max Act: 6.7340. Min Act: -0.1699
Data Index: 8136817 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2965. Min Range: -7.2965
Max Act: 6.7653. Min Act: -0.1698
Data Index: 3829701 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2965. Min Range: -7.2965
Max Act: 6.6715. Min Act: -0.1680
Data Index: 4838888 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2965. Min Range: -7.2965
Max Act: 6.7028. Min Act: -0.1698
Data Index: 4971600 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2965. Min Range: -7.2965
Max Act: 6.6715. Min Act: -0.1679
Data Index: 4787865 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2965. Min Range: -7.2965
Max Act: 6.6403. Min Act: -0.1700
Data Index: 3221336 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #19