Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4048 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.7876. Min Range: -8.7876
Max Act: 8.7876. Min Act: -0.1700
Data Index: 5908943 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7876. Min Range: -8.7876
Max Act: 8.7251. Min Act: -0.1700
Data Index: 5361241 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7876. Min Range: -8.7876
Max Act: 8.7876. Min Act: -0.1700
Data Index: 2712736 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7876. Min Range: -8.7876
Max Act: 8.7876. Min Act: -0.1700
Data Index: 5361227 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7876. Min Range: -8.7876
Max Act: 8.7251. Min Act: -0.1700
Data Index: 3069805 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7876. Min Range: -8.7876
Max Act: 8.7251. Min Act: -0.1699
Data Index: 7114330 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7876. Min Range: -8.7876
Max Act: 8.4751. Min Act: -0.1700
Data Index: 7397652 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7876. Min Range: -8.7876
Max Act: 8.3501. Min Act: -0.1700
Data Index: 1815763 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7876. Min Range: -8.7876
Max Act: 8.4126. Min Act: -0.1700
Data Index: 5555843 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7876. Min Range: -8.7876
Max Act: 8.3501. Min Act: -0.1683
Data Index: 1672080 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7876. Min Range: -8.7876
Max Act: 8.4126. Min Act: -0.1700
Data Index: 5361224 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7876. Min Range: -8.7876
Max Act: 8.3501. Min Act: -0.1700
Data Index: 1186212 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7876. Min Range: -8.7876
Max Act: 8.3501. Min Act: -0.1700
Data Index: 8644680 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7876. Min Range: -8.7876
Max Act: 8.3501. Min Act: -0.1700
Data Index: 4683012 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7876. Min Range: -8.7876
Max Act: 8.2876. Min Act: -0.1700
Data Index: 3888455 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7876. Min Range: -8.7876
Max Act: 8.3501. Min Act: -0.1700
Data Index: 286502 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7876. Min Range: -8.7876
Max Act: 8.2251. Min Act: -0.1700
Data Index: 6189738 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7876. Min Range: -8.7876
Max Act: 8.2251. Min Act: -0.1700
Data Index: 8367079 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7876. Min Range: -8.7876
Max Act: 8.2251. Min Act: -0.1700
Data Index: 4861231 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7876. Min Range: -8.7876
Max Act: 8.2251. Min Act: -0.1698
Data Index: 7991718 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #19