Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3446 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.6767. Min Range: -7.6767
Max Act: 7.6767. Min Act: -0.1700
Data Index: 8578641 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6767. Min Range: -7.6767
Max Act: 7.4892. Min Act: -0.1700
Data Index: 6915871 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6767. Min Range: -7.6767
Max Act: 7.4892. Min Act: -0.1700
Data Index: 7061283 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6767. Min Range: -7.6767
Max Act: 7.4267. Min Act: -0.1700
Data Index: 3575920 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6767. Min Range: -7.6767
Max Act: 7.4267. Min Act: -0.1700
Data Index: 4099571 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6767. Min Range: -7.6767
Max Act: 7.3642. Min Act: -0.1700
Data Index: 4358703 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6767. Min Range: -7.6767
Max Act: 7.3642. Min Act: -0.1700
Data Index: 8660081 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6767. Min Range: -7.6767
Max Act: 7.3642. Min Act: -0.1700
Data Index: 7729079 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6767. Min Range: -7.6767
Max Act: 7.3642. Min Act: -0.1700
Data Index: 3297012 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6767. Min Range: -7.6767
Max Act: 7.3642. Min Act: -0.1700
Data Index: 3063333 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6767. Min Range: -7.6767
Max Act: 7.3642. Min Act: -0.1700
Data Index: 2020314 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6767. Min Range: -7.6767
Max Act: 7.2079. Min Act: -0.1700
Data Index: 2275813 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6767. Min Range: -7.6767
Max Act: 7.3017. Min Act: -0.1700
Data Index: 8396751 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6767. Min Range: -7.6767
Max Act: 7.3017. Min Act: -0.1700
Data Index: 1276587 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6767. Min Range: -7.6767
Max Act: 7.2392. Min Act: -0.1700
Data Index: 8107985 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6767. Min Range: -7.6767
Max Act: 7.2392. Min Act: -0.1700
Data Index: 8112043 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6767. Min Range: -7.6767
Max Act: 7.2392. Min Act: -0.1700
Data Index: 8057833 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6767. Min Range: -7.6767
Max Act: 7.2079. Min Act: -0.1700
Data Index: 6566494 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6767. Min Range: -7.6767
Max Act: 7.2392. Min Act: -0.1700
Data Index: 1301182 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6767. Min Range: -7.6767
Max Act: 7.2392. Min Act: -0.1700
Data Index: 7896473 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #19