Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2287 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.4785. Min Range: -8.4785
Max Act: 8.4785. Min Act: -0.1700
Data Index: 5736745 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4785. Min Range: -8.4785
Max Act: 8.0410. Min Act: -0.1700
Data Index: 5861296 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4785. Min Range: -8.4785
Max Act: 7.9785. Min Act: -0.1700
Data Index: 8075105 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4785. Min Range: -8.4785
Max Act: 7.9160. Min Act: -0.1700
Data Index: 5488358 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4785. Min Range: -8.4785
Max Act: 7.9785. Min Act: -0.1700
Data Index: 5153392 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4785. Min Range: -8.4785
Max Act: 7.9160. Min Act: -0.1700
Data Index: 4372528 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4785. Min Range: -8.4785
Max Act: 7.9160. Min Act: -0.1700
Data Index: 2386319 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4785. Min Range: -8.4785
Max Act: 7.8535. Min Act: -0.1700
Data Index: 3103686 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4785. Min Range: -8.4785
Max Act: 7.8535. Min Act: -0.1700
Data Index: 1789630 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4785. Min Range: -8.4785
Max Act: 7.8222. Min Act: -0.1700
Data Index: 6987107 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4785. Min Range: -8.4785
Max Act: 7.7910. Min Act: -0.1700
Data Index: 7957011 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4785. Min Range: -8.4785
Max Act: 7.7910. Min Act: -0.1700
Data Index: 6147859 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4785. Min Range: -8.4785
Max Act: 7.7910. Min Act: -0.1700
Data Index: 3660919 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4785. Min Range: -8.4785
Max Act: 7.7597. Min Act: -0.1700
Data Index: 2876044 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4785. Min Range: -8.4785
Max Act: 7.7285. Min Act: -0.1700
Data Index: 6138443 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4785. Min Range: -8.4785
Max Act: 7.7285. Min Act: -0.1700
Data Index: 687186 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4785. Min Range: -8.4785
Max Act: 7.7597. Min Act: -0.1700
Data Index: 2031074 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4785. Min Range: -8.4785
Max Act: 7.7285. Min Act: -0.1700
Data Index: 6761009 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4785. Min Range: -8.4785
Max Act: 7.7285. Min Act: -0.1700
Data Index: 3492264 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4785. Min Range: -8.4785
Max Act: 7.6972. Min Act: -0.1700
Data Index: 6320320 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #19