Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 656 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.5619. Min Range: -1.5619
Max Act: 1.5619. Min Act: -0.1700
Data Index: 5333435 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5619. Min Range: -1.5619
Max Act: 1.4741. Min Act: -0.1700
Data Index: 3443350 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5619. Min Range: -1.5619
Max Act: 1.4741. Min Act: -0.1700
Data Index: 6526266 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5619. Min Range: -1.5619
Max Act: 1.4829. Min Act: -0.1669
Data Index: 7299351 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5619. Min Range: -1.5619
Max Act: 1.4478. Min Act: -0.1700
Data Index: 1305611 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5619. Min Range: -1.5619
Max Act: 1.4566. Min Act: -0.1687
Data Index: 6201620 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5619. Min Range: -1.5619
Max Act: 1.4478. Min Act: -0.1689
Data Index: 4188032 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5619. Min Range: -1.5619
Max Act: 1.4478. Min Act: -0.1699
Data Index: 3252992 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5619. Min Range: -1.5619
Max Act: 1.4390. Min Act: -0.1700
Data Index: 2216883 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5619. Min Range: -1.5619
Max Act: 1.4214. Min Act: -0.1696
Data Index: 2499761 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5619. Min Range: -1.5619
Max Act: 1.4037. Min Act: -0.1700
Data Index: 5816352 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5619. Min Range: -1.5619
Max Act: 1.4126. Min Act: -0.1697
Data Index: 3959442 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5619. Min Range: -1.5619
Max Act: 1.4214. Min Act: -0.1700
Data Index: 6695400 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5619. Min Range: -1.5619
Max Act: 1.4126. Min Act: -0.1700
Data Index: 4054985 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5619. Min Range: -1.5619
Max Act: 1.4126. Min Act: -0.1564
Data Index: 6525092 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5619. Min Range: -1.5619
Max Act: 1.4126. Min Act: -0.1700
Data Index: 3247653 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5619. Min Range: -1.5619
Max Act: 1.4037. Min Act: -0.1700
Data Index: 1184765 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5619. Min Range: -1.5619
Max Act: 1.4126. Min Act: -0.1700
Data Index: 2676418 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5619. Min Range: -1.5619
Max Act: 1.4037. Min Act: -0.1700
Data Index: 8117841 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5619. Min Range: -1.5619
Max Act: 1.4037. Min Act: -0.1700
Data Index: 1145606 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #19