Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 74 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.7950. Min Range: -3.7950
Max Act: 3.7950. Min Act: -0.1700
Data Index: 3327561 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7950. Min Range: -3.7950
Max Act: 3.7012. Min Act: -0.1700
Data Index: 3663697 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7950. Min Range: -3.7950
Max Act: 3.7012. Min Act: -0.1700
Data Index: 6959873 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7950. Min Range: -3.7950
Max Act: 3.7012. Min Act: -0.1700
Data Index: 5712480 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7950. Min Range: -3.7950
Max Act: 3.7012. Min Act: -0.1700
Data Index: 7671607 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7950. Min Range: -3.7950
Max Act: 3.6699. Min Act: -0.1700
Data Index: 1092071 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7950. Min Range: -3.7950
Max Act: 3.6699. Min Act: -0.1700
Data Index: 5772922 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7950. Min Range: -3.7950
Max Act: 3.6699. Min Act: -0.1700
Data Index: 6505728 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7950. Min Range: -3.7950
Max Act: 3.6699. Min Act: -0.1700
Data Index: 7263108 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7950. Min Range: -3.7950
Max Act: 3.6699. Min Act: -0.1700
Data Index: 591655 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7950. Min Range: -3.7950
Max Act: 3.6699. Min Act: -0.1700
Data Index: 7126408 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7950. Min Range: -3.7950
Max Act: 3.6386. Min Act: -0.1700
Data Index: 4379391 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7950. Min Range: -3.7950
Max Act: 3.6386. Min Act: -0.1700
Data Index: 5046021 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7950. Min Range: -3.7950
Max Act: 3.6386. Min Act: -0.1700
Data Index: 5057954 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7950. Min Range: -3.7950
Max Act: 3.6386. Min Act: -0.1700
Data Index: 6561084 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7950. Min Range: -3.7950
Max Act: 3.6699. Min Act: -0.1700
Data Index: 2463647 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7950. Min Range: -3.7950
Max Act: 3.6386. Min Act: -0.1700
Data Index: 7015108 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7950. Min Range: -3.7950
Max Act: 3.6386. Min Act: -0.1700
Data Index: 115528 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7950. Min Range: -3.7950
Max Act: 3.6386. Min Act: -0.1699
Data Index: 3251843 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7950. Min Range: -3.7950
Max Act: 3.6386. Min Act: -0.1700
Data Index: 7103930 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19