Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2569 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6094. Min Range: -4.6094
Max Act: 4.6094. Min Act: -0.1700
Data Index: 6794264 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6094. Min Range: -4.6094
Max Act: 4.5782. Min Act: -0.1700
Data Index: 4849903 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6094. Min Range: -4.6094
Max Act: 4.5469. Min Act: -0.1700
Data Index: 1316586 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6094. Min Range: -4.6094
Max Act: 4.5157. Min Act: -0.1699
Data Index: 1160312 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6094. Min Range: -4.6094
Max Act: 4.5157. Min Act: -0.1700
Data Index: 1074053 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6094. Min Range: -4.6094
Max Act: 4.4844. Min Act: -0.1700
Data Index: 6908456 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6094. Min Range: -4.6094
Max Act: 4.4844. Min Act: -0.1694
Data Index: 8547100 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6094. Min Range: -4.6094
Max Act: 4.4532. Min Act: -0.1700
Data Index: 2588860 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6094. Min Range: -4.6094
Max Act: 4.4532. Min Act: -0.1700
Data Index: 5578764 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6094. Min Range: -4.6094
Max Act: 4.4532. Min Act: -0.1700
Data Index: 5869342 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6094. Min Range: -4.6094
Max Act: 4.4219. Min Act: -0.1700
Data Index: 968444 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6094. Min Range: -4.6094
Max Act: 4.4219. Min Act: -0.1700
Data Index: 916751 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6094. Min Range: -4.6094
Max Act: 4.4219. Min Act: -0.1700
Data Index: 589046 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6094. Min Range: -4.6094
Max Act: 4.4219. Min Act: -0.1700
Data Index: 911792 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6094. Min Range: -4.6094
Max Act: 4.4219. Min Act: -0.1685
Data Index: 59947 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6094. Min Range: -4.6094
Max Act: 4.4219. Min Act: -0.1700
Data Index: 138521 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6094. Min Range: -4.6094
Max Act: 4.4219. Min Act: -0.1699
Data Index: 578762 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6094. Min Range: -4.6094
Max Act: 4.4219. Min Act: -0.1700
Data Index: 723074 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6094. Min Range: -4.6094
Max Act: 4.4219. Min Act: -0.1700
Data Index: 27792 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6094. Min Range: -4.6094
Max Act: 4.4219. Min Act: -0.1699
Data Index: 637877 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19