Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2881 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.7235. Min Range: -5.7235
Max Act: 5.7235. Min Act: -0.1700
Data Index: 4410771 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7235. Min Range: -5.7235
Max Act: 5.6922. Min Act: -0.1699
Data Index: 8575917 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7235. Min Range: -5.7235
Max Act: 5.6297. Min Act: -0.1700
Data Index: 1101504 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7235. Min Range: -5.7235
Max Act: 5.6297. Min Act: -0.1688
Data Index: 1638128 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7235. Min Range: -5.7235
Max Act: 5.5985. Min Act: -0.1699
Data Index: 4282754 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7235. Min Range: -5.7235
Max Act: 5.5985. Min Act: -0.1700
Data Index: 2131752 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7235. Min Range: -5.7235
Max Act: 5.5985. Min Act: -0.1693
Data Index: 3472622 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7235. Min Range: -5.7235
Max Act: 5.5985. Min Act: -0.1700
Data Index: 1089196 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7235. Min Range: -5.7235
Max Act: 5.5672. Min Act: -0.1698
Data Index: 1751310 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7235. Min Range: -5.7235
Max Act: 5.5672. Min Act: -0.1698
Data Index: 8440128 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7235. Min Range: -5.7235
Max Act: 5.5360. Min Act: -0.1700
Data Index: 1466823 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7235. Min Range: -5.7235
Max Act: 5.5672. Min Act: -0.1700
Data Index: 7613528 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7235. Min Range: -5.7235
Max Act: 5.5672. Min Act: -0.1686
Data Index: 7792468 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7235. Min Range: -5.7235
Max Act: 5.5360. Min Act: -0.1700
Data Index: 2438700 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7235. Min Range: -5.7235
Max Act: 5.5672. Min Act: -0.1700
Data Index: 1012191 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7235. Min Range: -5.7235
Max Act: 5.5672. Min Act: -0.1700
Data Index: 1992121 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7235. Min Range: -5.7235
Max Act: 5.5360. Min Act: -0.1700
Data Index: 8333747 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7235. Min Range: -5.7235
Max Act: 5.5360. Min Act: -0.1694
Data Index: 7885430 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7235. Min Range: -5.7235
Max Act: 5.5360. Min Act: -0.1700
Data Index: 3163535 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7235. Min Range: -5.7235
Max Act: 5.5360. Min Act: -0.1700
Data Index: 178156 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19