Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3613 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.0220. Min Range: -8.0220
Max Act: 8.0220. Min Act: -0.1700
Data Index: 6002246 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0220. Min Range: -8.0220
Max Act: 7.9595. Min Act: -0.1700
Data Index: 7390622 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0220. Min Range: -8.0220
Max Act: 7.7095. Min Act: -0.1700
Data Index: 210303 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0220. Min Range: -8.0220
Max Act: 7.7095. Min Act: -0.1700
Data Index: 3953627 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0220. Min Range: -8.0220
Max Act: 7.5533. Min Act: -0.1700
Data Index: 3025443 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0220. Min Range: -8.0220
Max Act: 7.5220. Min Act: -0.1700
Data Index: 7284997 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0220. Min Range: -8.0220
Max Act: 7.5220. Min Act: -0.1700
Data Index: 8092612 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0220. Min Range: -8.0220
Max Act: 7.4908. Min Act: -0.1700
Data Index: 6359556 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0220. Min Range: -8.0220
Max Act: 7.4595. Min Act: -0.1700
Data Index: 7840456 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0220. Min Range: -8.0220
Max Act: 7.3970. Min Act: -0.1700
Data Index: 4314356 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0220. Min Range: -8.0220
Max Act: 7.4283. Min Act: -0.1700
Data Index: 3444633 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0220. Min Range: -8.0220
Max Act: 7.3970. Min Act: -0.1700
Data Index: 5128181 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0220. Min Range: -8.0220
Max Act: 7.3658. Min Act: -0.1700
Data Index: 5242351 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0220. Min Range: -8.0220
Max Act: 7.3658. Min Act: -0.1700
Data Index: 5680713 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0220. Min Range: -8.0220
Max Act: 7.3345. Min Act: -0.1700
Data Index: 3282808 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0220. Min Range: -8.0220
Max Act: 7.3658. Min Act: -0.1700
Data Index: 5940475 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0220. Min Range: -8.0220
Max Act: 7.3970. Min Act: -0.1700
Data Index: 5593928 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0220. Min Range: -8.0220
Max Act: 7.3658. Min Act: -0.1700
Data Index: 759017 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0220. Min Range: -8.0220
Max Act: 7.3658. Min Act: -0.1700
Data Index: 7962455 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0220. Min Range: -8.0220
Max Act: 7.3658. Min Act: -0.1700
Data Index: 4779447 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #19