Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4641 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.7023. Min Range: -5.7023
Max Act: 5.7023. Min Act: -0.1700
Data Index: 7917901 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7023. Min Range: -5.7023
Max Act: 5.7023. Min Act: -0.1697
Data Index: 3633433 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7023. Min Range: -5.7023
Max Act: 5.6398. Min Act: -0.1700
Data Index: 8473042 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7023. Min Range: -5.7023
Max Act: 5.6710. Min Act: -0.1700
Data Index: 6967827 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7023. Min Range: -5.7023
Max Act: 5.6398. Min Act: -0.1700
Data Index: 5946412 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7023. Min Range: -5.7023
Max Act: 5.6710. Min Act: -0.1700
Data Index: 2878406 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7023. Min Range: -5.7023
Max Act: 5.6710. Min Act: -0.1700
Data Index: 4832561 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7023. Min Range: -5.7023
Max Act: 5.6398. Min Act: -0.1700
Data Index: 5990079 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7023. Min Range: -5.7023
Max Act: 5.6398. Min Act: -0.1700
Data Index: 6212105 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7023. Min Range: -5.7023
Max Act: 5.6398. Min Act: -0.1700
Data Index: 2589437 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7023. Min Range: -5.7023
Max Act: 5.6085. Min Act: -0.1700
Data Index: 109911 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7023. Min Range: -5.7023
Max Act: 5.6085. Min Act: -0.1700
Data Index: 1136474 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7023. Min Range: -5.7023
Max Act: 5.6085. Min Act: -0.1700
Data Index: 4173282 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7023. Min Range: -5.7023
Max Act: 5.5773. Min Act: -0.1700
Data Index: 5847510 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7023. Min Range: -5.7023
Max Act: 5.5773. Min Act: -0.1700
Data Index: 2888724 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7023. Min Range: -5.7023
Max Act: 5.5773. Min Act: -0.1700
Data Index: 7166958 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7023. Min Range: -5.7023
Max Act: 5.6085. Min Act: -0.1700
Data Index: 7176814 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7023. Min Range: -5.7023
Max Act: 5.5773. Min Act: -0.1700
Data Index: 7901119 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7023. Min Range: -5.7023
Max Act: 5.5773. Min Act: -0.1700
Data Index: 3358345 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7023. Min Range: -5.7023
Max Act: 5.6085. Min Act: -0.1700
Data Index: 4138788 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19