Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5418 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 17.8286. Min Range: -17.8286
Max Act: 17.8286. Min Act: -0.1699
Data Index: 2037172 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 17.8286. Min Range: -17.8286
Max Act: 17.7036. Min Act: -0.1699
Data Index: 131759 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 17.8286. Min Range: -17.8286
Max Act: 17.7036. Min Act: -0.1700
Data Index: 5691063 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 17.8286. Min Range: -17.8286
Max Act: 17.7036. Min Act: -0.1681
Data Index: 2774093 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 17.8286. Min Range: -17.8286
Max Act: 17.5786. Min Act: -0.1698
Data Index: 2174179 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 17.8286. Min Range: -17.8286
Max Act: 17.5786. Min Act: -0.1700
Data Index: 2898279 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 17.8286. Min Range: -17.8286
Max Act: 17.5786. Min Act: -0.1700
Data Index: 105693 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 17.8286. Min Range: -17.8286
Max Act: 17.5786. Min Act: -0.1700
Data Index: 3555166 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 17.8286. Min Range: -17.8286
Max Act: 17.5786. Min Act: -0.1700
Data Index: 7359752 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 17.8286. Min Range: -17.8286
Max Act: 17.4536. Min Act: -0.1700
Data Index: 2224208 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 17.8286. Min Range: -17.8286
Max Act: 17.4536. Min Act: -0.1661
Data Index: 1575650 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 17.8286. Min Range: -17.8286
Max Act: 17.4536. Min Act: -0.1697
Data Index: 971043 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 17.8286. Min Range: -17.8286
Max Act: 17.4536. Min Act: -0.1680
Data Index: 2932104 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 17.8286. Min Range: -17.8286
Max Act: 17.4536. Min Act: -0.1668
Data Index: 3391765 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 17.8286. Min Range: -17.8286
Max Act: 17.4536. Min Act: -0.1688
Data Index: 4367585 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 17.8286. Min Range: -17.8286
Max Act: 17.4536. Min Act: -0.1685
Data Index: 4415957 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 17.8286. Min Range: -17.8286
Max Act: 17.4536. Min Act: -0.1680
Data Index: 4713612 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 17.8286. Min Range: -17.8286
Max Act: 17.4536. Min Act: -0.1699
Data Index: 5191477 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 17.8286. Min Range: -17.8286
Max Act: 17.4536. Min Act: -0.1700
Data Index: 1498347 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 17.8286. Min Range: -17.8286
Max Act: 17.4536. Min Act: -0.1651
Data Index: 658443 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #19