Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 16 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5096. Min Range: -4.5096
Max Act: 4.5096. Min Act: -0.1700
Data Index: 4920634 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5096. Min Range: -4.5096
Max Act: 4.4471. Min Act: -0.1700
Data Index: 1251023 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5096. Min Range: -4.5096
Max Act: 4.4159. Min Act: -0.1700
Data Index: 1080889 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5096. Min Range: -4.5096
Max Act: 4.3221. Min Act: -0.1700
Data Index: 997000 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5096. Min Range: -4.5096
Max Act: 4.3846. Min Act: -0.1700
Data Index: 4296228 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5096. Min Range: -4.5096
Max Act: 4.2909. Min Act: -0.1700
Data Index: 1022907 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5096. Min Range: -4.5096
Max Act: 4.3221. Min Act: -0.1700
Data Index: 1311058 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5096. Min Range: -4.5096
Max Act: 4.2284. Min Act: -0.1700
Data Index: 1238691 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5096. Min Range: -4.5096
Max Act: 4.1659. Min Act: -0.1700
Data Index: 235953 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5096. Min Range: -4.5096
Max Act: 4.1971. Min Act: -0.1700
Data Index: 5488937 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5096. Min Range: -4.5096
Max Act: 4.1971. Min Act: -0.1700
Data Index: 5663849 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5096. Min Range: -4.5096
Max Act: 4.1971. Min Act: -0.1700
Data Index: 3927343 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5096. Min Range: -4.5096
Max Act: 4.1659. Min Act: -0.1700
Data Index: 747739 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5096. Min Range: -4.5096
Max Act: 4.1659. Min Act: -0.1700
Data Index: 7896925 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5096. Min Range: -4.5096
Max Act: 4.1346. Min Act: -0.1700
Data Index: 3556634 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5096. Min Range: -4.5096
Max Act: 4.1346. Min Act: -0.1700
Data Index: 2318077 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5096. Min Range: -4.5096
Max Act: 4.1659. Min Act: -0.1700
Data Index: 706796 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5096. Min Range: -4.5096
Max Act: 4.1346. Min Act: -0.1700
Data Index: 7746090 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5096. Min Range: -4.5096
Max Act: 4.1659. Min Act: -0.1700
Data Index: 1068158 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5096. Min Range: -4.5096
Max Act: 4.1033. Min Act: -0.1700
Data Index: 1917880 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #19