Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3553 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.4803. Min Range: -3.4803
Max Act: 3.4803. Min Act: -0.1700
Data Index: 2998122 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4803. Min Range: -3.4803
Max Act: 3.4803. Min Act: -0.1700
Data Index: 8425908 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4803. Min Range: -3.4803
Max Act: 3.4803. Min Act: -0.1700
Data Index: 4024927 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4803. Min Range: -3.4803
Max Act: 3.4803. Min Act: -0.1700
Data Index: 1268790 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4803. Min Range: -3.4803
Max Act: 3.4803. Min Act: -0.1700
Data Index: 5443452 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4803. Min Range: -3.4803
Max Act: 3.4490. Min Act: -0.1700
Data Index: 8778653 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4803. Min Range: -3.4803
Max Act: 3.4803. Min Act: -0.1700
Data Index: 6432739 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4803. Min Range: -3.4803
Max Act: 3.4490. Min Act: -0.1700
Data Index: 6196715 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4803. Min Range: -3.4803
Max Act: 3.4490. Min Act: -0.1700
Data Index: 8653134 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4803. Min Range: -3.4803
Max Act: 3.4490. Min Act: -0.1700
Data Index: 8037844 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4803. Min Range: -3.4803
Max Act: 3.4490. Min Act: -0.1700
Data Index: 265652 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4803. Min Range: -3.4803
Max Act: 3.4490. Min Act: -0.1700
Data Index: 7782598 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4803. Min Range: -3.4803
Max Act: 3.4490. Min Act: -0.1700
Data Index: 7106537 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4803. Min Range: -3.4803
Max Act: 3.4490. Min Act: -0.1700
Data Index: 6277805 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4803. Min Range: -3.4803
Max Act: 3.4490. Min Act: -0.1700
Data Index: 55815 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4803. Min Range: -3.4803
Max Act: 3.4490. Min Act: -0.1700
Data Index: 4571331 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4803. Min Range: -3.4803
Max Act: 3.4490. Min Act: -0.1700
Data Index: 3452505 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4803. Min Range: -3.4803
Max Act: 3.4490. Min Act: -0.1700
Data Index: 998792 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4803. Min Range: -3.4803
Max Act: 3.4490. Min Act: -0.1700
Data Index: 3408364 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4803. Min Range: -3.4803
Max Act: 3.4490. Min Act: -0.1700
Data Index: 846388 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #19