Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3122 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4925. Min Range: -5.4925
Max Act: 5.4925. Min Act: -0.1700
Data Index: 5329736 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4925. Min Range: -5.4925
Max Act: 5.4300. Min Act: -0.1700
Data Index: 5931139 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4925. Min Range: -5.4925
Max Act: 5.4300. Min Act: -0.1700
Data Index: 6443695 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4925. Min Range: -5.4925
Max Act: 5.3988. Min Act: -0.1700
Data Index: 281443 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4925. Min Range: -5.4925
Max Act: 5.3988. Min Act: -0.1700
Data Index: 6370993 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4925. Min Range: -5.4925
Max Act: 5.3988. Min Act: -0.1700
Data Index: 5657794 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4925. Min Range: -5.4925
Max Act: 5.3988. Min Act: -0.1700
Data Index: 4945060 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4925. Min Range: -5.4925
Max Act: 5.3988. Min Act: -0.1700
Data Index: 4946526 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4925. Min Range: -5.4925
Max Act: 5.3675. Min Act: -0.1700
Data Index: 1775294 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4925. Min Range: -5.4925
Max Act: 5.3675. Min Act: -0.1700
Data Index: 4457771 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4925. Min Range: -5.4925
Max Act: 5.3675. Min Act: -0.1698
Data Index: 770191 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4925. Min Range: -5.4925
Max Act: 5.3988. Min Act: -0.1700
Data Index: 7740130 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4925. Min Range: -5.4925
Max Act: 5.3675. Min Act: -0.1700
Data Index: 2443961 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4925. Min Range: -5.4925
Max Act: 5.3675. Min Act: -0.1700
Data Index: 2826973 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4925. Min Range: -5.4925
Max Act: 5.3675. Min Act: -0.1700
Data Index: 2275186 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4925. Min Range: -5.4925
Max Act: 5.3363. Min Act: -0.1700
Data Index: 1831402 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4925. Min Range: -5.4925
Max Act: 5.3363. Min Act: -0.1700
Data Index: 5500412 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4925. Min Range: -5.4925
Max Act: 5.3363. Min Act: -0.1700
Data Index: 3804065 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4925. Min Range: -5.4925
Max Act: 5.3363. Min Act: -0.1700
Data Index: 3971409 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4925. Min Range: -5.4925
Max Act: 5.3363. Min Act: -0.1700
Data Index: 2191901 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19