Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 29 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5715. Min Range: -5.5715
Max Act: 5.5715. Min Act: -0.1700
Data Index: 517259 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5715. Min Range: -5.5715
Max Act: 5.4465. Min Act: -0.1700
Data Index: 1914732 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5715. Min Range: -5.5715
Max Act: 5.3528. Min Act: -0.1700
Data Index: 1380625 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5715. Min Range: -5.5715
Max Act: 5.3840. Min Act: -0.1700
Data Index: 6828918 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5715. Min Range: -5.5715
Max Act: 5.3840. Min Act: -0.1700
Data Index: 6828916 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5715. Min Range: -5.5715
Max Act: 5.3528. Min Act: -0.1700
Data Index: 1875727 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5715. Min Range: -5.5715
Max Act: 5.2903. Min Act: -0.1700
Data Index: 1038189 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5715. Min Range: -5.5715
Max Act: 5.2590. Min Act: -0.1700
Data Index: 7154617 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5715. Min Range: -5.5715
Max Act: 5.2903. Min Act: -0.1700
Data Index: 4274729 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5715. Min Range: -5.5715
Max Act: 5.2903. Min Act: -0.1700
Data Index: 860691 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5715. Min Range: -5.5715
Max Act: 5.2590. Min Act: -0.1700
Data Index: 3758768 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5715. Min Range: -5.5715
Max Act: 5.2590. Min Act: -0.1700
Data Index: 3811030 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5715. Min Range: -5.5715
Max Act: 5.2278. Min Act: -0.1700
Data Index: 2269373 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5715. Min Range: -5.5715
Max Act: 5.2278. Min Act: -0.1700
Data Index: 3740754 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5715. Min Range: -5.5715
Max Act: 5.2278. Min Act: -0.1700
Data Index: 6758083 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5715. Min Range: -5.5715
Max Act: 5.2278. Min Act: -0.1700
Data Index: 6500700 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5715. Min Range: -5.5715
Max Act: 5.1965. Min Act: -0.1700
Data Index: 363326 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5715. Min Range: -5.5715
Max Act: 5.1965. Min Act: -0.1700
Data Index: 3686237 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5715. Min Range: -5.5715
Max Act: 5.1653. Min Act: -0.1700
Data Index: 4148868 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5715. Min Range: -5.5715
Max Act: 5.1965. Min Act: -0.1700
Data Index: 2259670 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #19