Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1387 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.8019. Min Range: -5.8019
Max Act: 5.8019. Min Act: -0.1700
Data Index: 4445698 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8019. Min Range: -5.8019
Max Act: 5.7706. Min Act: -0.1700
Data Index: 816023 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8019. Min Range: -5.8019
Max Act: 5.7706. Min Act: -0.1700
Data Index: 5070404 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8019. Min Range: -5.8019
Max Act: 5.7081. Min Act: -0.1699
Data Index: 1133773 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8019. Min Range: -5.8019
Max Act: 5.7394. Min Act: -0.1700
Data Index: 1077838 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8019. Min Range: -5.8019
Max Act: 5.7394. Min Act: -0.1700
Data Index: 579814 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8019. Min Range: -5.8019
Max Act: 5.7081. Min Act: -0.1700
Data Index: 7897751 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8019. Min Range: -5.8019
Max Act: 5.6769. Min Act: -0.1699
Data Index: 1562529 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8019. Min Range: -5.8019
Max Act: 5.7081. Min Act: -0.1700
Data Index: 5573653 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8019. Min Range: -5.8019
Max Act: 5.7081. Min Act: -0.1700
Data Index: 3012411 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8019. Min Range: -5.8019
Max Act: 5.6769. Min Act: -0.1700
Data Index: 5384170 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8019. Min Range: -5.8019
Max Act: 5.6769. Min Act: -0.1700
Data Index: 3983091 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8019. Min Range: -5.8019
Max Act: 5.6769. Min Act: -0.1700
Data Index: 6705340 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8019. Min Range: -5.8019
Max Act: 5.6769. Min Act: -0.1700
Data Index: 1926881 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8019. Min Range: -5.8019
Max Act: 5.6769. Min Act: -0.1700
Data Index: 6221133 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8019. Min Range: -5.8019
Max Act: 5.6769. Min Act: -0.1700
Data Index: 894753 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8019. Min Range: -5.8019
Max Act: 5.6456. Min Act: -0.1700
Data Index: 78114 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8019. Min Range: -5.8019
Max Act: 5.6769. Min Act: -0.1700
Data Index: 90765 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8019. Min Range: -5.8019
Max Act: 5.6456. Min Act: -0.1700
Data Index: 5949707 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8019. Min Range: -5.8019
Max Act: 5.6456. Min Act: -0.1692
Data Index: 736460 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19