Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1972 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0743. Min Range: -4.0743
Max Act: 4.0743. Min Act: -0.1700
Data Index: 3528713 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0743. Min Range: -4.0743
Max Act: 4.0118. Min Act: -0.1700
Data Index: 6778731 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0743. Min Range: -4.0743
Max Act: 3.9805. Min Act: -0.1700
Data Index: 292549 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0743. Min Range: -4.0743
Max Act: 3.8554. Min Act: -0.1700
Data Index: 3056353 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0743. Min Range: -4.0743
Max Act: 3.9023. Min Act: -0.1700
Data Index: 1249679 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0743. Min Range: -4.0743
Max Act: 3.8554. Min Act: -0.1700
Data Index: 5243814 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0743. Min Range: -4.0743
Max Act: 3.7929. Min Act: -0.1700
Data Index: 7950811 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0743. Min Range: -4.0743
Max Act: 3.8085. Min Act: -0.1700
Data Index: 5928570 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0743. Min Range: -4.0743
Max Act: 3.7616. Min Act: -0.1700
Data Index: 7768779 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0743. Min Range: -4.0743
Max Act: 3.7303. Min Act: -0.1700
Data Index: 7228421 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0743. Min Range: -4.0743
Max Act: 3.7460. Min Act: -0.1700
Data Index: 5723993 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0743. Min Range: -4.0743
Max Act: 3.7303. Min Act: -0.1700
Data Index: 4333748 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0743. Min Range: -4.0743
Max Act: 3.7147. Min Act: -0.1700
Data Index: 2430281 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0743. Min Range: -4.0743
Max Act: 3.7147. Min Act: -0.1700
Data Index: 2915520 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0743. Min Range: -4.0743
Max Act: 3.7616. Min Act: -0.1700
Data Index: 3703451 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0743. Min Range: -4.0743
Max Act: 3.6991. Min Act: -0.1700
Data Index: 3522135 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0743. Min Range: -4.0743
Max Act: 3.7147. Min Act: -0.1700
Data Index: 5287936 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0743. Min Range: -4.0743
Max Act: 3.6521. Min Act: -0.1700
Data Index: 2482316 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0743. Min Range: -4.0743
Max Act: 3.6991. Min Act: -0.1700
Data Index: 6760080 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0743. Min Range: -4.0743
Max Act: 3.6678. Min Act: -0.1700
Data Index: 706687 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #19