Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3134 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4022. Min Range: -3.4022
Max Act: 3.4022. Min Act: -0.1700
Data Index: 7367927 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4022. Min Range: -3.4022
Max Act: 3.3865. Min Act: -0.1700
Data Index: 1503990 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4022. Min Range: -3.4022
Max Act: 3.3708. Min Act: -0.1700
Data Index: 7174977 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4022. Min Range: -3.4022
Max Act: 3.3551. Min Act: -0.1700
Data Index: 7001262 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4022. Min Range: -3.4022
Max Act: 3.3394. Min Act: -0.1700
Data Index: 3197704 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4022. Min Range: -3.4022
Max Act: 3.3394. Min Act: -0.1700
Data Index: 4115716 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4022. Min Range: -3.4022
Max Act: 3.3394. Min Act: -0.1700
Data Index: 8807478 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4022. Min Range: -3.4022
Max Act: 3.3237. Min Act: -0.1700
Data Index: 2298726 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4022. Min Range: -3.4022
Max Act: 3.3237. Min Act: -0.1700
Data Index: 4403766 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4022. Min Range: -3.4022
Max Act: 3.3080. Min Act: -0.1700
Data Index: 5353652 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4022. Min Range: -3.4022
Max Act: 3.3080. Min Act: -0.1700
Data Index: 4558159 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4022. Min Range: -3.4022
Max Act: 3.3080. Min Act: -0.1700
Data Index: 2965954 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4022. Min Range: -3.4022
Max Act: 3.2923. Min Act: -0.1700
Data Index: 2134668 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4022. Min Range: -3.4022
Max Act: 3.3080. Min Act: -0.1700
Data Index: 8408877 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4022. Min Range: -3.4022
Max Act: 3.3080. Min Act: -0.1700
Data Index: 7698760 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4022. Min Range: -3.4022
Max Act: 3.2923. Min Act: -0.1700
Data Index: 5956200 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4022. Min Range: -3.4022
Max Act: 3.2923. Min Act: -0.1700
Data Index: 5352223 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4022. Min Range: -3.4022
Max Act: 3.2923. Min Act: -0.1700
Data Index: 7001143 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4022. Min Range: -3.4022
Max Act: 3.2923. Min Act: -0.1700
Data Index: 5120511 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4022. Min Range: -3.4022
Max Act: 3.2766. Min Act: -0.1700
Data Index: 6052268 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19