Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3689 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 0.2903. Min Range: -0.2903
Max Act: 0.2903. Min Act: -0.1700
Data Index: 2479004 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.2903. Min Range: -0.2903
Max Act: 0.2339. Min Act: -0.1700
Data Index: 7464865 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.2903. Min Range: -0.2903
Max Act: 0.2339. Min Act: -0.1693
Data Index: 8405401 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.2903. Min Range: -0.2903
Max Act: 0.2279. Min Act: -0.1700
Data Index: 3423998 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.2903. Min Range: -0.2903
Max Act: 0.2279. Min Act: -0.1700
Data Index: 2479005 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.2903. Min Range: -0.2903
Max Act: 0.2041. Min Act: -0.1700
Data Index: 3493083 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.2903. Min Range: -0.2903
Max Act: 0.1896. Min Act: -0.1657
Data Index: 6410080 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.2903. Min Range: -0.2903
Max Act: 0.1953. Min Act: -0.1700
Data Index: 2655790 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.2903. Min Range: -0.2903
Max Act: 0.1924. Min Act: -0.1700
Data Index: 7750817 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.2903. Min Range: -0.2903
Max Act: 0.1896. Min Act: -0.1700
Data Index: 6108477 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.2903. Min Range: -0.2903
Max Act: 0.1810. Min Act: -0.1696
Data Index: 1703707 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.2903. Min Range: -0.2903
Max Act: 0.1896. Min Act: -0.1700
Data Index: 5168742 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.2903. Min Range: -0.2903
Max Act: 0.1896. Min Act: -0.1690
Data Index: 524892 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.2903. Min Range: -0.2903
Max Act: 0.1838. Min Act: -0.1664
Data Index: 908879 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.2903. Min Range: -0.2903
Max Act: 0.1810. Min Act: -0.1700
Data Index: 6499164 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.2903. Min Range: -0.2903
Max Act: 0.1838. Min Act: -0.1685
Data Index: 4750157 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.2903. Min Range: -0.2903
Max Act: 0.1781. Min Act: -0.1669
Data Index: 1950539 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.2903. Min Range: -0.2903
Max Act: 0.1781. Min Act: -0.1697
Data Index: 5036401 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.2903. Min Range: -0.2903
Max Act: 0.1753. Min Act: -0.1679
Data Index: 6563611 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.2903. Min Range: -0.2903
Max Act: 0.1781. Min Act: -0.1700
Data Index: 820098 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #19