Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1735 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.1656. Min Range: -1.1656
Max Act: 1.1656. Min Act: -0.1700
Data Index: 8759035 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.1656. Min Range: -1.1656
Max Act: 1.1041. Min Act: -0.1700
Data Index: 8240973 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.1656. Min Range: -1.1656
Max Act: 1.0953. Min Act: -0.1700
Data Index: 3552848 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.1656. Min Range: -1.1656
Max Act: 1.0691. Min Act: -0.1700
Data Index: 1512400 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.1656. Min Range: -1.1656
Max Act: 1.0778. Min Act: -0.1700
Data Index: 956905 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.1656. Min Range: -1.1656
Max Act: 1.0691. Min Act: -0.1700
Data Index: 945281 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.1656. Min Range: -1.1656
Max Act: 1.0604. Min Act: -0.1700
Data Index: 7980520 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.1656. Min Range: -1.1656
Max Act: 1.0429. Min Act: -0.1700
Data Index: 7443963 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.1656. Min Range: -1.1656
Max Act: 1.0604. Min Act: -0.1700
Data Index: 6793750 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.1656. Min Range: -1.1656
Max Act: 1.0429. Min Act: -0.1700
Data Index: 4887448 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.1656. Min Range: -1.1656
Max Act: 1.0342. Min Act: -0.1700
Data Index: 8671301 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.1656. Min Range: -1.1656
Max Act: 1.0516. Min Act: -0.1700
Data Index: 839991 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.1656. Min Range: -1.1656
Max Act: 1.0516. Min Act: -0.1700
Data Index: 8159299 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.1656. Min Range: -1.1656
Max Act: 1.0342. Min Act: -0.1700
Data Index: 5654812 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.1656. Min Range: -1.1656
Max Act: 1.0342. Min Act: -0.1700
Data Index: 2571293 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.1656. Min Range: -1.1656
Max Act: 1.0342. Min Act: -0.1700
Data Index: 6734818 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.1656. Min Range: -1.1656
Max Act: 1.0255. Min Act: -0.1700
Data Index: 8283812 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.1656. Min Range: -1.1656
Max Act: 1.0255. Min Act: -0.1700
Data Index: 6273292 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.1656. Min Range: -1.1656
Max Act: 1.0168. Min Act: -0.1700
Data Index: 2841930 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.1656. Min Range: -1.1656
Max Act: 1.0168. Min Act: -0.1700
Data Index: 4797387 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #19