Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2189 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3747. Min Range: -5.3747
Max Act: 5.3747. Min Act: -0.1700
Data Index: 865535 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3747. Min Range: -5.3747
Max Act: 5.2810. Min Act: -0.1700
Data Index: 4927550 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3747. Min Range: -5.3747
Max Act: 5.1560. Min Act: -0.1700
Data Index: 3025863 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3747. Min Range: -5.3747
Max Act: 5.0935. Min Act: -0.1700
Data Index: 3839157 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3747. Min Range: -5.3747
Max Act: 5.0935. Min Act: -0.1700
Data Index: 1030603 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3747. Min Range: -5.3747
Max Act: 5.0310. Min Act: -0.1700
Data Index: 8544599 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3747. Min Range: -5.3747
Max Act: 4.9997. Min Act: -0.1700
Data Index: 1652432 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3747. Min Range: -5.3747
Max Act: 5.0310. Min Act: -0.1700
Data Index: 4652742 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3747. Min Range: -5.3747
Max Act: 4.9997. Min Act: -0.1700
Data Index: 745659 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3747. Min Range: -5.3747
Max Act: 4.9997. Min Act: -0.1700
Data Index: 6220696 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3747. Min Range: -5.3747
Max Act: 4.9685. Min Act: -0.1700
Data Index: 8625513 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3747. Min Range: -5.3747
Max Act: 4.9685. Min Act: -0.1700
Data Index: 6794502 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3747. Min Range: -5.3747
Max Act: 4.9685. Min Act: -0.1700
Data Index: 321701 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3747. Min Range: -5.3747
Max Act: 4.9372. Min Act: -0.1700
Data Index: 1424941 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3747. Min Range: -5.3747
Max Act: 4.9372. Min Act: -0.1700
Data Index: 6495886 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3747. Min Range: -5.3747
Max Act: 4.9372. Min Act: -0.1700
Data Index: 1665282 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3747. Min Range: -5.3747
Max Act: 4.9060. Min Act: -0.1700
Data Index: 3969753 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3747. Min Range: -5.3747
Max Act: 4.9060. Min Act: -0.1700
Data Index: 7845436 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3747. Min Range: -5.3747
Max Act: 4.9060. Min Act: -0.1700
Data Index: 306385 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3747. Min Range: -5.3747
Max Act: 4.9372. Min Act: -0.1700
Data Index: 4053806 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #19