Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3991 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.0698. Min Range: -3.0698
Max Act: 3.0698. Min Act: -0.1700
Data Index: 7191990 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0698. Min Range: -3.0698
Max Act: 3.0225. Min Act: -0.1700
Data Index: 1641492 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0698. Min Range: -3.0698
Max Act: 2.9117. Min Act: -0.1700
Data Index: 2936443 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0698. Min Range: -3.0698
Max Act: 2.8642. Min Act: -0.1700
Data Index: 3825175 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0698. Min Range: -3.0698
Max Act: 2.8483. Min Act: -0.1700
Data Index: 7085109 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0698. Min Range: -3.0698
Max Act: 2.8642. Min Act: -0.1700
Data Index: 6765549 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0698. Min Range: -3.0698
Max Act: 2.8642. Min Act: -0.1700
Data Index: 6453086 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0698. Min Range: -3.0698
Max Act: 2.8483. Min Act: -0.1700
Data Index: 2023120 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0698. Min Range: -3.0698
Max Act: 2.8165. Min Act: -0.1700
Data Index: 5820395 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0698. Min Range: -3.0698
Max Act: 2.8165. Min Act: -0.1700
Data Index: 8813253 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0698. Min Range: -3.0698
Max Act: 2.8324. Min Act: -0.1700
Data Index: 5245482 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0698. Min Range: -3.0698
Max Act: 2.8483. Min Act: -0.1700
Data Index: 7495827 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0698. Min Range: -3.0698
Max Act: 2.8324. Min Act: -0.1700
Data Index: 2987167 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0698. Min Range: -3.0698
Max Act: 2.8324. Min Act: -0.1700
Data Index: 5480518 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0698. Min Range: -3.0698
Max Act: 2.8005. Min Act: -0.1700
Data Index: 7229628 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0698. Min Range: -3.0698
Max Act: 2.8165. Min Act: -0.1700
Data Index: 3762227 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0698. Min Range: -3.0698
Max Act: 2.8005. Min Act: -0.1700
Data Index: 1879306 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0698. Min Range: -3.0698
Max Act: 2.8005. Min Act: -0.1700
Data Index: 2961704 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0698. Min Range: -3.0698
Max Act: 2.8005. Min Act: -0.1700
Data Index: 1891405 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0698. Min Range: -3.0698
Max Act: 2.8165. Min Act: -0.1700
Data Index: 38987 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #19