Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2886 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2331. Min Range: -4.2331
Max Act: 4.2331. Min Act: -0.1700
Data Index: 5725722 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2331. Min Range: -4.2331
Max Act: 4.2019. Min Act: -0.1700
Data Index: 8114691 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2331. Min Range: -4.2331
Max Act: 4.1081. Min Act: -0.1700
Data Index: 1379075 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2331. Min Range: -4.2331
Max Act: 4.0768. Min Act: -0.1700
Data Index: 1616488 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2331. Min Range: -4.2331
Max Act: 4.0456. Min Act: -0.1700
Data Index: 5419866 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2331. Min Range: -4.2331
Max Act: 4.0143. Min Act: -0.1700
Data Index: 4037722 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2331. Min Range: -4.2331
Max Act: 3.9831. Min Act: -0.1700
Data Index: 8007387 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2331. Min Range: -4.2331
Max Act: 3.9831. Min Act: -0.1700
Data Index: 1580833 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2331. Min Range: -4.2331
Max Act: 3.9831. Min Act: -0.1700
Data Index: 8007386 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2331. Min Range: -4.2331
Max Act: 3.9831. Min Act: -0.1700
Data Index: 5226102 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2331. Min Range: -4.2331
Max Act: 4.0143. Min Act: -0.1700
Data Index: 3566869 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2331. Min Range: -4.2331
Max Act: 3.9831. Min Act: -0.1700
Data Index: 5037513 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2331. Min Range: -4.2331
Max Act: 3.9518. Min Act: -0.1700
Data Index: 8207177 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2331. Min Range: -4.2331
Max Act: 3.9518. Min Act: -0.1700
Data Index: 1408416 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2331. Min Range: -4.2331
Max Act: 3.9518. Min Act: -0.1700
Data Index: 7161235 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2331. Min Range: -4.2331
Max Act: 3.8893. Min Act: -0.1700
Data Index: 7957713 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2331. Min Range: -4.2331
Max Act: 3.9205. Min Act: -0.1700
Data Index: 5178623 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2331. Min Range: -4.2331
Max Act: 3.9205. Min Act: -0.1700
Data Index: 8586272 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2331. Min Range: -4.2331
Max Act: 3.9205. Min Act: -0.1700
Data Index: 3378996 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2331. Min Range: -4.2331
Max Act: 3.8893. Min Act: -0.1700
Data Index: 5552896 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #19