Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1681 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0065. Min Range: -4.0065
Max Act: 4.0065. Min Act: -0.1700
Data Index: 234625 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0065. Min Range: -4.0065
Max Act: 3.9440. Min Act: -0.1700
Data Index: 8686686 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0065. Min Range: -4.0065
Max Act: 3.9440. Min Act: -0.1700
Data Index: 1496673 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0065. Min Range: -4.0065
Max Act: 3.9127. Min Act: -0.1700
Data Index: 3119648 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0065. Min Range: -4.0065
Max Act: 3.9127. Min Act: -0.1700
Data Index: 838296 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0065. Min Range: -4.0065
Max Act: 3.9127. Min Act: -0.1700
Data Index: 7796814 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0065. Min Range: -4.0065
Max Act: 3.9127. Min Act: -0.1700
Data Index: 8675532 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0065. Min Range: -4.0065
Max Act: 3.9127. Min Act: -0.1700
Data Index: 357029 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0065. Min Range: -4.0065
Max Act: 3.8814. Min Act: -0.1700
Data Index: 475093 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0065. Min Range: -4.0065
Max Act: 3.8814. Min Act: -0.1700
Data Index: 206274 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0065. Min Range: -4.0065
Max Act: 3.8502. Min Act: -0.1700
Data Index: 1802936 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0065. Min Range: -4.0065
Max Act: 3.8502. Min Act: -0.1700
Data Index: 2125477 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0065. Min Range: -4.0065
Max Act: 3.8502. Min Act: -0.1700
Data Index: 3131384 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0065. Min Range: -4.0065
Max Act: 3.8189. Min Act: -0.1700
Data Index: 721150 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0065. Min Range: -4.0065
Max Act: 3.8502. Min Act: -0.1700
Data Index: 4106479 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0065. Min Range: -4.0065
Max Act: 3.8502. Min Act: -0.1700
Data Index: 1575058 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0065. Min Range: -4.0065
Max Act: 3.8814. Min Act: -0.1700
Data Index: 4730312 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0065. Min Range: -4.0065
Max Act: 3.8814. Min Act: -0.1700
Data Index: 3904645 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0065. Min Range: -4.0065
Max Act: 3.8502. Min Act: -0.1700
Data Index: 2682145 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0065. Min Range: -4.0065
Max Act: 3.8189. Min Act: -0.1700
Data Index: 7071647 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #19