Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1476 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7698. Min Range: -4.7698
Max Act: 4.7698. Min Act: -0.1700
Data Index: 2652100 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7698. Min Range: -4.7698
Max Act: 4.7073. Min Act: -0.1700
Data Index: 535024 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7698. Min Range: -4.7698
Max Act: 4.6760. Min Act: -0.1700
Data Index: 7710514 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7698. Min Range: -4.7698
Max Act: 4.6135. Min Act: -0.1700
Data Index: 4439901 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7698. Min Range: -4.7698
Max Act: 4.5823. Min Act: -0.1700
Data Index: 3275577 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7698. Min Range: -4.7698
Max Act: 4.6135. Min Act: -0.1700
Data Index: 966062 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7698. Min Range: -4.7698
Max Act: 4.6135. Min Act: -0.1700
Data Index: 7743812 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7698. Min Range: -4.7698
Max Act: 4.5823. Min Act: -0.1700
Data Index: 8653621 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7698. Min Range: -4.7698
Max Act: 4.5823. Min Act: -0.1700
Data Index: 2696780 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7698. Min Range: -4.7698
Max Act: 4.5823. Min Act: -0.1700
Data Index: 1339425 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7698. Min Range: -4.7698
Max Act: 4.5823. Min Act: -0.1700
Data Index: 6621494 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7698. Min Range: -4.7698
Max Act: 4.5823. Min Act: -0.1700
Data Index: 1470035 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7698. Min Range: -4.7698
Max Act: 4.6135. Min Act: -0.1700
Data Index: 3507459 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7698. Min Range: -4.7698
Max Act: 4.5823. Min Act: -0.1700
Data Index: 6559820 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7698. Min Range: -4.7698
Max Act: 4.5198. Min Act: -0.1700
Data Index: 6980823 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7698. Min Range: -4.7698
Max Act: 4.5510. Min Act: -0.1700
Data Index: 5382332 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7698. Min Range: -4.7698
Max Act: 4.5823. Min Act: -0.1700
Data Index: 7197945 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7698. Min Range: -4.7698
Max Act: 4.5510. Min Act: -0.1700
Data Index: 3146659 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7698. Min Range: -4.7698
Max Act: 4.5823. Min Act: -0.1700
Data Index: 5750481 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7698. Min Range: -4.7698
Max Act: 4.5510. Min Act: -0.1700
Data Index: 3320780 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #19