Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 194 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1903. Min Range: -5.1903
Max Act: 5.1903. Min Act: -0.1700
Data Index: 1278122 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1903. Min Range: -5.1903
Max Act: 4.9715. Min Act: -0.1700
Data Index: 1803578 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1903. Min Range: -5.1903
Max Act: 4.9715. Min Act: -0.1700
Data Index: 7468683 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1903. Min Range: -5.1903
Max Act: 4.9715. Min Act: -0.1700
Data Index: 1718113 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1903. Min Range: -5.1903
Max Act: 4.9715. Min Act: -0.1700
Data Index: 239250 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1903. Min Range: -5.1903
Max Act: 4.9090. Min Act: -0.1700
Data Index: 188603 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1903. Min Range: -5.1903
Max Act: 4.9715. Min Act: -0.1700
Data Index: 5048661 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1903. Min Range: -5.1903
Max Act: 4.9403. Min Act: -0.1700
Data Index: 144128 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1903. Min Range: -5.1903
Max Act: 4.9090. Min Act: -0.1700
Data Index: 4451370 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1903. Min Range: -5.1903
Max Act: 4.9090. Min Act: -0.1700
Data Index: 5718748 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1903. Min Range: -5.1903
Max Act: 4.9090. Min Act: -0.1700
Data Index: 7322548 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1903. Min Range: -5.1903
Max Act: 4.9090. Min Act: -0.1700
Data Index: 1579964 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1903. Min Range: -5.1903
Max Act: 4.9403. Min Act: -0.1700
Data Index: 6270155 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1903. Min Range: -5.1903
Max Act: 4.8778. Min Act: -0.1700
Data Index: 7996794 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1903. Min Range: -5.1903
Max Act: 4.8465. Min Act: -0.1700
Data Index: 1216604 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1903. Min Range: -5.1903
Max Act: 4.9090. Min Act: -0.1700
Data Index: 2129402 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1903. Min Range: -5.1903
Max Act: 4.8778. Min Act: -0.1700
Data Index: 8336290 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1903. Min Range: -5.1903
Max Act: 4.8778. Min Act: -0.1700
Data Index: 8227772 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1903. Min Range: -5.1903
Max Act: 4.8465. Min Act: -0.1700
Data Index: 552438 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1903. Min Range: -5.1903
Max Act: 4.8153. Min Act: -0.1700
Data Index: 6920675 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #19