Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5068 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.2104. Min Range: -2.2104
Max Act: 2.2104. Min Act: -0.1700
Data Index: 3082205 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2104. Min Range: -2.2104
Max Act: 2.1938. Min Act: -0.1700
Data Index: 7610880 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2104. Min Range: -2.2104
Max Act: 2.1438. Min Act: -0.1700
Data Index: 3794540 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2104. Min Range: -2.2104
Max Act: 2.1438. Min Act: -0.1700
Data Index: 4314868 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2104. Min Range: -2.2104
Max Act: 2.1272. Min Act: -0.1700
Data Index: 5394812 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2104. Min Range: -2.2104
Max Act: 2.1104. Min Act: -0.1700
Data Index: 7610881 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2104. Min Range: -2.2104
Max Act: 2.0937. Min Act: -0.1700
Data Index: 4432164 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2104. Min Range: -2.2104
Max Act: 2.0937. Min Act: -0.1700
Data Index: 3746742 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2104. Min Range: -2.2104
Max Act: 2.0937. Min Act: -0.1700
Data Index: 2621513 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2104. Min Range: -2.2104
Max Act: 2.0937. Min Act: -0.1700
Data Index: 6224429 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2104. Min Range: -2.2104
Max Act: 2.0769. Min Act: -0.1700
Data Index: 385295 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2104. Min Range: -2.2104
Max Act: 2.0769. Min Act: -0.1700
Data Index: 12694 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2104. Min Range: -2.2104
Max Act: 2.0769. Min Act: -0.1700
Data Index: 5899517 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2104. Min Range: -2.2104
Max Act: 2.0601. Min Act: -0.1700
Data Index: 1783074 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2104. Min Range: -2.2104
Max Act: 2.0601. Min Act: -0.1700
Data Index: 745811 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2104. Min Range: -2.2104
Max Act: 2.0601. Min Act: -0.1700
Data Index: 6470548 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2104. Min Range: -2.2104
Max Act: 2.0601. Min Act: -0.1700
Data Index: 4613822 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2104. Min Range: -2.2104
Max Act: 2.0601. Min Act: -0.1700
Data Index: 2352443 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2104. Min Range: -2.2104
Max Act: 2.0601. Min Act: -0.1700
Data Index: 3474066 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2104. Min Range: -2.2104
Max Act: 2.0601. Min Act: -0.1700
Data Index: 3679667 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #19